{"version": "2.1.0", "$schema": "https://json.schemastore.org/sarif-2.1.0.json", "runs": [{"tool": {"driver": {"name": "Repobility", "informationUri": "https://repobility.com", "rules": [{"id": "scanner-b8263e9f0e19a497", "name": "Possibly dead Python function: lin2s", "shortDescription": {"text": "Possibly dead Python function: lin2s"}, "fullDescription": {"text": "No callers detected by AST scan in this repo. Could be exported for external callers or a framework handler."}, "properties": {"scanner": "scanner-primary", "layer": "software", "severity": "low", "confidence": 1.0}}, {"id": "scanner-e7496589e2b9ff68", "name": "Agent instruction/config may expose a secret: Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md", "shortDescription": {"text": "Agent instruction/config may expose a secret: Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "fullDescription": {"text": "Agent-facing files are routinely pasted into LLM/tool contexts. Move literal tokens, keys, and passwords into a secret manager or document them as placeholders only."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 1.0}}, {"id": "scanner-72eb7e7dc8d20e9e", "name": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md", "shortDescription": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md"}, "fullDescription": {"text": "This agent instruction grants code or shell authority but does not state the verification gate that decides promotion. The recurring safe pattern is: LLM proposes; deterministic tests/build/security checks verify; only verified code promotes."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}, {"id": "scanner-9e35e425c83c8ed7", "name": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md", "shortDescription": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "fullDescription": {"text": "This agent instruction grants code or shell authority but does not state the verification gate that decides promotion. The recurring safe pattern is: LLM proposes; deterministic tests/build/security checks verify; only verified code promotes."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}, {"id": "scanner-2f25281023ac0841", "name": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/storybook/SKILL.md", "shortDescription": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/storybook/SKILL.md"}, "fullDescription": {"text": "This agent instruction grants code or shell authority but does not state the verification gate that decides promotion. The recurring safe pattern is: LLM proposes; deterministic tests/build/security checks verify; only verified code promotes."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}, {"id": "scanner-b0dd92c2e032f924", "name": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md", "shortDescription": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "fullDescription": {"text": "This agent instruction grants code or shell authority but does not state the verification gate that decides promotion. The recurring safe pattern is: LLM proposes; deterministic tests/build/security checks verify; only verified code promotes."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}, {"id": "scanner-44533f9ddb4bf0fa", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/curl/examples.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/curl/examples.md"}, "fullDescription": {"text": "cURL / Raw HTTP\n\nUse these examples when the user needs raw HTTP requests or is working in a language without an official SDK.\n\n## Setup\n\n```bash\nexport ANTHROPIC_API_KEY=\"your-api-key\"\n```\n\n---\n\n## B\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.60\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.6}}, {"id": "scanner-26d29b77d20cfd9f", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/curl/managed-agents.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/curl/managed-agents.md"}, "fullDescription": {"text": "cURL / Raw HTTP\n\nUse these examples when the user needs raw HTTP requests or is working without an SDK.\n\n## Setup\n\n```bash\nexport ANTHROPIC_API_KEY=\"your-api-key\"\n\n# Common headers\nHEADERS=(\n  -H \"Con\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.60\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.6}}, {"id": "scanner-5142746dd2d3c7c2", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/go/managed-agents/README.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/go/managed-agents/README.md"}, "fullDescription": {"text": "https://api.githubcopilot.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-4e1f87d29758252e", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/java/managed-agents/README.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/java/managed-agents/README.md"}, "fullDescription": {"text": "https://api.githubcopilot.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-78d5a466fa906fff", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/php/managed-agents/README.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/php/managed-agents/README.md"}, "fullDescription": {"text": "https://api.anthropic.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-8e9d1a862f7cee1a", "name": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md", "shortDescription": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md"}, "fullDescription": {"text": "send the full conversation history\n\nCode or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.\n\nSkill: claude-api\nRule: E4  Category: data-exfil\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-787eb51095d30365", "name": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/python/managed-agents/README.md", "shortDescription": {"text": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/python/managed-agents/README.md"}, "fullDescription": {"text": "os.environ[\"GITHUB_TOKEN\"]\n\nCode accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.\n\nSkill: claude-api\nRule: E2  Category: data-exfil\nSeverity: HIGH  Confidence: 0.80\n\nRemediation: Avoid reading sensitive env vars (API keys, tokens) unless strictly required. Use secrets managers or secure config. Never log or transmit credentials."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.8}}, {"id": "scanner-d11397e135f76617", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/ruby/managed-agents/README.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/ruby/managed-agents/README.md"}, "fullDescription": {"text": "https://api.githubcopilot.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-0224924703c756a4", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "fullDescription": {"text": "curl https://api.anthropic.com/v1/messages \\\n  -H \"Authorization: Bearer $(ant auth print-credentials --access-token)\" \\\n  -H \"anthropic-version: 2023-06-01\" \\\n  -H \"anthropic-beta: oauth-2025-04-20\"\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.60\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.6}}, {"id": "scanner-159db39500b4a4ce", "name": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/live-sources.md", "shortDescription": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/live-sources.md"}, "fullDescription": {"text": "Extract context\n\nCode or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.\n\nSkill: claude-api\nRule: E4  Category: data-exfil\nSeverity: HIGH  Confidence: 0.75\n\nRemediation: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.75}}, {"id": "scanner-28ea41bc622ec69a", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-api-reference.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-api-reference.md"}, "fullDescription": {"text": "https://api.githubcopilot.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-5e510ebf6dbc9b26", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "fullDescription": {"text": "https://api.githubcopilot.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-cd7a8253f49692e8", "name": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md", "shortDescription": {"text": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "fullDescription": {"text": "os.environ[\"GITHUB_TOKEN\"]\n\nCode accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.\n\nSkill: claude-api\nRule: E2  Category: data-exfil\nSeverity: HIGH  Confidence: 0.80\n\nRemediation: Avoid reading sensitive env vars (API keys, tokens) unless strictly required. Use secrets managers or secure config. Never log or transmit credentials."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.8}}, {"id": "scanner-1ba28e1d7f8b652c", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-scheduled-deployme", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-scheduled-deployments.md"}, "fullDescription": {"text": "curl -fsSL https://api.anthropic.com/v1/deployments \\\n  -H \"x-api-key: $ANTHROPIC_API_KEY\" \\\n  -H \"anthropic-version: 2023-06-01\" \\\n  -H \"anthropic-beta: managed-agents-2026-04-01\" \\\n  -H \"content-typ\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.60\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.6}}, {"id": "scanner-9e6b1a1450328661", "name": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-self-hosted-sandbo", "shortDescription": {"text": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-self-hosted-sandboxes.md"}, "fullDescription": {"text": "os.environ[\"ANTHROPIC_ENVIRONMENT_KEY\"]\n\nCode accesses environment variables that may contain secrets (API keys, tokens). This is a common pattern for credential theft.\n\nSkill: claude-api\nRule: E2  Category: data-exfil\nSeverity: HIGH  Confidence: 0.80\n\nRemediation: Avoid reading sensitive env vars (API keys, tokens) unless strictly required. Use secrets managers or secure config. Never log or transmit credentials."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.8}}, {"id": "scanner-8f336bada82af29d", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "fullDescription": {"text": "https://api.notion.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-057305514468c795", "name": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md", "shortDescription": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md"}, "fullDescription": {"text": "send the conversation\n\nCode or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.\n\nSkill: claude-api\nRule: E4  Category: data-exfil\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-98a5e8748ede1724", "name": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/models.md", "shortDescription": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/models.md"}, "fullDescription": {"text": "https://api.anthropic.com/\n\nData is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.\n\nSkill: claude-api\nRule: E1  Category: data-exfil\nSeverity: MEDIUM  Confidence: 0.50\n\nRemediation: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.5}}, {"id": "scanner-5525aaa724037c51", "name": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/typescript/claude-api/README.md", "shortDescription": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/typescript/claude-api/README.md"}, "fullDescription": {"text": "send the full conversation history\n\nCode or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.\n\nSkill: claude-api\nRule: E4  Category: data-exfil\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-37bf457f31be4e3f", "name": "SkillSpector EA3 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/LICENSE.txt", "shortDescription": {"text": "SkillSpector EA3 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/LICENSE.txt"}, "fullDescription": {"text": "not limited to\n\nSkill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.\n\nSkill: claude-api\nRule: EA3  Category: excessive-agency\nSeverity: LOW  Confidence: 0.70\n\nRemediation: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "low", "confidence": 0.7}}, {"id": "scanner-a88831714e0bcf71", "name": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md", "shortDescription": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "fullDescription": {"text": "don't ask the user\n\nSkill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.\n\nSkill: claude-api\nRule: EA2  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.80\n\nRemediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.8}}, {"id": "scanner-eea1aebc8055f343", "name": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/go/claude-api/tool-use.md", "shortDescription": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/go/claude-api/tool-use.md"}, "fullDescription": {"text": "automatically\nrun\n\nSkill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.\n\nSkill: claude-api\nRule: EA2  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.80\n\nRemediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.8}}, {"id": "scanner-302bb8e3fbe179a0", "name": "SkillSpector EA4 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md", "shortDescription": {"text": "SkillSpector EA4 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md"}, "fullDescription": {"text": "max_retries=0\n\nSkill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.\n\nSkill: claude-api\nRule: EA4  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.80\n\nRemediation: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.8}}, {"id": "scanner-f3cf9348a037f9a4", "name": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/tool-use.md", "shortDescription": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/tool-use.md"}, "fullDescription": {"text": "automatically\nrun\n\nSkill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.\n\nSkill: claude-api\nRule: EA2  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.80\n\nRemediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.8}}, {"id": "scanner-c22abd8be8160863", "name": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md", "shortDescription": {"text": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md"}, "fullDescription": {"text": "tool:*\n\nSkill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.\n\nSkill: claude-api\nRule: EA1  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.85\n\nRemediation: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.85}}, {"id": "scanner-bf624f267c277a6f", "name": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md", "shortDescription": {"text": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "fullDescription": {"text": "tool:*\n\nSkill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.\n\nSkill: claude-api\nRule: EA1  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.85\n\nRemediation: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.85}}, {"id": "scanner-b44886185b845395", "name": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md", "shortDescription": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md"}, "fullDescription": {"text": "without asking\n\nSkill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.\n\nSkill: claude-api\nRule: EA2  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.75\n\nRemediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.75}}, {"id": "scanner-3f9963f15766966c", "name": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/tool-use-concepts.md", "shortDescription": {"text": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/tool-use-concepts.md"}, "fullDescription": {"text": "tools:*\n\nSkill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.\n\nSkill: claude-api\nRule: EA1  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.85\n\nRemediation: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.85}}, {"id": "scanner-619f6af183c80d8d", "name": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md", "shortDescription": {"text": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "fullDescription": {"text": "exceed context window\n\nSkill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.\n\nSkill: claude-api\nRule: MP2  Category: memory-poisoning\nSeverity: MEDIUM  Confidence: 0.80\n\nRemediation: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.8}}, {"id": "scanner-d5587e0c0da5465e", "name": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md", "shortDescription": {"text": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md"}, "fullDescription": {"text": "exceed the context window\n\nSkill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.\n\nSkill: claude-api\nRule: MP2  Category: memory-poisoning\nSeverity: MEDIUM  Confidence: 0.80\n\nRemediation: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.8}}, {"id": "scanner-ccf41afaf901fa58", "name": "SkillSpector PE2 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md", "shortDescription": {"text": "SkillSpector PE2 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "fullDescription": {"text": "sudo\n\nCommands invoke sudo or root privileges. Verify this elevated access is necessary and justified.\n\nSkill: claude-api\nRule: PE2  Category: priv-esc\nSeverity: MEDIUM  Confidence: 0.70\n\nRemediation: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.7}}, {"id": "scanner-0a6621bdd81ce15e", "name": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md", "shortDescription": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "fullDescription": {"text": ".env\n\nCode accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.\n\nSkill: claude-api\nRule: PE3  Category: priv-esc\nSeverity: HIGH  Confidence: 0.60\n\nRemediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.6}}, {"id": "scanner-ebc829283a442ba5", "name": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md", "shortDescription": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "fullDescription": {"text": "Access Token\n\nCode accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.\n\nSkill: claude-api\nRule: PE3  Category: priv-esc\nSeverity: HIGH  Confidence: 0.70\n\nRemediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.7}}, {"id": "scanner-d75a07facc8588c3", "name": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md", "shortDescription": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "fullDescription": {"text": "Access Tokens\n\nCode accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.\n\nSkill: claude-api\nRule: PE3  Category: priv-esc\nSeverity: HIGH  Confidence: 0.70\n\nRemediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.7}}, {"id": "scanner-304ef16ce4a64286", "name": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md", "shortDescription": {"text": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "fullDescription": {"text": "write `claude-fable-5` code, include the server-side `fallbacks` parameter by default** (`betas: [\"server-side-fallback-2026-06-01\"]` + `fallbacks: [{\"model\": \"claude-opus-4-8\"}]`; Claude API and Clau\n\nSkill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.\n\nSkill: claude-api\nRule: RA2  Category: rogue-agent\nSeverity: MEDIUM  Confidence: 0.60\n\nRemediation: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.6}}, {"id": "scanner-831a5338262cba55", "name": "SkillSpector TM2 (tool-misuse) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md", "shortDescription": {"text": "SkillSpector TM2 (tool-misuse) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "fullDescription": {"text": "| sudo\n\nTool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.\n\nSkill: claude-api\nRule: TM2  Category: tool-misuse\nSeverity: HIGH  Confidence: 0.75\n\nRemediation: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.75}}, {"id": "scanner-b5524b9516d07605", "name": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/design-sync/lib/sync-hashes.mjs", "shortDescription": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/design-sync/lib/sync-hashes.mjs"}, "fullDescription": {"text": "no verification\n\nSkill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.\n\nSkill: design-sync\nRule: EA2  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.75\n\nRemediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.75}}, {"id": "scanner-c824c1a6f3e019eb", "name": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md", "shortDescription": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "fullDescription": {"text": "without asking\n\nSkill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.\n\nSkill: design-sync\nRule: EA2  Category: excessive-agency\nSeverity: MEDIUM  Confidence: 0.75\n\nRemediation: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.75}}, {"id": "scanner-4f6ecd5bbbb7d38d", "name": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/design-sync/lib/common.mjs", "shortDescription": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/design-sync/lib/common.mjs"}, "fullDescription": {"text": ".env'\n\nCode accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.\n\nSkill: design-sync\nRule: PE3  Category: priv-esc\nSeverity: HIGH  Confidence: 0.60\n\nRemediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.6}}, {"id": "scanner-4f70436aa882c705", "name": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs", "shortDescription": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs"}, "fullDescription": {"text": "/etc/passwd\n\nCode accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.\n\nSkill: design-sync\nRule: PE3  Category: priv-esc\nSeverity: HIGH  Confidence: 0.60\n\nRemediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.6}}, {"id": "scanner-eff36cca435ff1cc", "name": "SkillSpector P2 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/lib/emit.mjs", "shortDescription": {"text": "SkillSpector P2 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/lib/emit.mjs"}, "fullDescription": {"text": "<!-- @dsCard group=\"${escapeHtml(group)}\"${viewportAttr} -->\n<!doctype html>\n<html><head><meta charset=\"utf-8\">\n  <link rel=\"stylesheet\" href=\"../../../styles.css\">${bundleCssLink}${previewCssLink}\n\nHidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.\n\nSkill: design-sync\nRule: P2  Category: prompt-injection\nSeverity: HIGH  Confidence: 0.70\n\nRemediation: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.7}}, {"id": "scanner-5f40c16936ca76dc", "name": "SkillSpector P2 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md", "shortDescription": {"text": "SkillSpector P2 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "fullDescription": {"text": "<!-- @dsCard group=\"\u2026\" -->` for the DS pane to register it. Usually a local `lib/emit.mjs` edit dropped the header \u2014 restore it, or re-run the converter. |\n| `[LINK_HREF_MISSING]` | `<path>: <link hre\n\nHidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.\n\nSkill: design-sync\nRule: P2  Category: prompt-injection\nSeverity: HIGH  Confidence: 0.70\n\nRemediation: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.7}}, {"id": "scanner-2201a0896e408b97", "name": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md", "shortDescription": {"text": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md"}, "fullDescription": {"text": "defaults write\n\nSkill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.\n\nSkill: design-sync\nRule: RA2  Category: rogue-agent\nSeverity: MEDIUM  Confidence: 0.75\n\nRemediation: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.75}}, {"id": "scanner-afa7315cb5586e47", "name": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/design-sync/lib/source-kit.mjs", "shortDescription": {"text": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/design-sync/lib/source-kit.mjs"}, "fullDescription": {"text": "defaults write\n\nSkill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.\n\nSkill: design-sync\nRule: RA2  Category: rogue-agent\nSeverity: MEDIUM  Confidence: 0.75\n\nRemediation: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.75}}, {"id": "scanner-c7f1e67f3033ee2b", "name": "SkillSpector P6 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs", "shortDescription": {"text": "SkillSpector P6 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs"}, "fullDescription": {"text": "return rules\n\nSkill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.\n\nSkill: design-sync\nRule: P6  Category: prompt-injection\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-2415a3d8869eef89", "name": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/lib/preview-rebuild.mjs", "shortDescription": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/lib/preview-rebuild.mjs"}, "fullDescription": {"text": "rm -rf's the whole bundle and must stay\n/\n\nTool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).\n\nSkill: design-sync\nRule: TM1  Category: tool-misuse\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-c010cc119ae79d23", "name": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md", "shortDescription": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "fullDescription": {"text": "rm <path>` | `--out` points at `/\n\nTool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).\n\nSkill: design-sync\nRule: TM1  Category: tool-misuse\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-260dcb99b8b367ab", "name": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/package-build.mjs", "shortDescription": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/package-build.mjs"}, "fullDescription": {"text": "rm -rf cwd, $HOME, /, anything in the durable\n/\n\nTool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).\n\nSkill: design-sync\nRule: TM1  Category: tool-misuse\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-bbdd0c81a4d188cd", "name": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/playwright.md", "shortDescription": {"text": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/playwright.md"}, "fullDescription": {"text": "fill input\n\nSkill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.\n\nSkill: run-skill-generator\nRule: MP2  Category: memory-poisoning\nSeverity: MEDIUM  Confidence: 0.85\n\nRemediation: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "medium", "confidence": 0.85}}, {"id": "scanner-61b434bed383a1cb", "name": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md", "shortDescription": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "fullDescription": {"text": "keychain\n\nCode accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.\n\nSkill: run-skill-generator\nRule: PE3  Category: priv-esc\nSeverity: HIGH  Confidence: 0.70\n\nRemediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.7}}, {"id": "scanner-af04ee15f59f3478", "name": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md", "shortDescription": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "fullDescription": {"text": "keychain\n\nCode accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.\n\nSkill: run-skill-generator\nRule: PE3  Category: priv-esc\nSeverity: HIGH  Confidence: 0.70\n\nRemediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.7}}, {"id": "scanner-5eeba6a45ea9a7da", "name": "SkillSpector RA1 (rogue-agent) in Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md", "shortDescription": {"text": "SkillSpector RA1 (rogue-agent) in Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "fullDescription": {"text": "Write SKILL\n\nSkill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.\n\nSkill: run-skill-generator\nRule: RA1  Category: rogue-agent\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-534fa5305f9624c0", "name": "SkillSpector RA1 (rogue-agent) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md", "shortDescription": {"text": "SkillSpector RA1 (rogue-agent) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "fullDescription": {"text": "write SKILL\n\nSkill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.\n\nSkill: run-skill-generator\nRule: RA1  Category: rogue-agent\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-a7a8f60edcf2216e", "name": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md", "shortDescription": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "fullDescription": {"text": "rm -f /tmp/\n\nTool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).\n\nSkill: run-skill-generator\nRule: TM1  Category: tool-misuse\nSeverity: HIGH  Confidence: 0.85\n\nRemediation: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 0.85}}, {"id": "scanner-e637c415447867e4", "name": "Run SkillSpector's LLM-backed analysis in your own pipeline", "shortDescription": {"text": "Run SkillSpector's LLM-backed analysis in your own pipeline"}, "fullDescription": {"text": "Repobility ran SkillSpector's static rules server-side. The deeper LLM-backed analyzers \u2014 tool-poisoning (TP*), semantic security discovery (SSD*), developer-intent mismatch (SDI*) \u2014 are meant to run on YOUR machine with YOUR model; repobility never sends your code to an LLM. Recipe:\n\n# 1. Install SkillSpector in your own isolated env\npipx install \"skillspector @ git+https://github.com/NVIDIA/SkillSpector.git\"\n\n# 2. Point it at YOUR LLM pipeline (pick one) - your code stays on your machine\nexport SKILLSPECTOR_PROVIDER=anthropic && export ANTHROPIC_API_KEY=sk-ant-...\n# export SKILLSPECTOR_PROVIDER=openai   && export OPENAI_API_KEY=sk-...\n# export SKILLSPECTOR_PROVIDER=openai OPENAI_API_KEY=ollama OPENAI_BASE_URL=http://localhost:11434/v1 SKILLSPECTOR_MODEL=llama3.1:8b\n# export SKILLSPECTOR_PROVIDER=nv_build && export NVIDIA_INFERENCE_KEY=nvapi-...\n\n# 3. Run the LLM-backed scan per skill (omit --no-llm to enable the LLM analyzers)\nskillspector scan Anthropic/Claude Code/bundled-skills/cl"}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "info", "confidence": 1.0}}, {"id": "scanner-2fb77ce69f44a2a2", "name": "Insecure pattern 'new_function_used' in Anthropic/Claude Code/bundled-skills/design-sync/package-validate.mjs:65", "shortDescription": {"text": "Insecure pattern 'new_function_used' in Anthropic/Claude Code/bundled-skills/design-sync/package-validate.mjs:65"}, "fullDescription": {"text": "Found a known-risky pattern (new_function_used). Review and replace if possible."}, "properties": {"scanner": "scanner-primary", "layer": "security", "severity": "high", "confidence": 1.0}}, {"id": "scanner-4ff4adf982755127", "name": "Very large file: Anthropic/Claude Code/bundled-skills/design-sync/package-build.mjs (1005 lines)", "shortDescription": {"text": "Very large file: Anthropic/Claude Code/bundled-skills/design-sync/package-build.mjs (1005 lines)"}, "fullDescription": {"text": "Files with >800 lines often hide complexity hotspots and discourage tests."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "low", "confidence": 1.0}}, {"id": "scanner-63d60c4fae83e340", "name": "Very large file: Anthropic/Claude Code/bundled-skills/design-sync/package-validate.mjs (804 lines)", "shortDescription": {"text": "Very large file: Anthropic/Claude Code/bundled-skills/design-sync/package-validate.mjs (804 lines)"}, "fullDescription": {"text": "Files with >800 lines often hide complexity hotspots and discourage tests."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "low", "confidence": 1.0}}, {"id": "scanner-6893a6c8b0861585", "name": "Very low test-to-source ratio", "shortDescription": {"text": "Very low test-to-source ratio"}, "fullDescription": {"text": "0 test file(s) for 28 source file(s) (ratio 0.00). Consider adding integration or unit tests for critical paths."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}, {"id": "scanner-3ab5d313dda8e5f9", "name": "Debug logging residue appears in source files", "shortDescription": {"text": "Debug logging residue appears in source files"}, "fullDescription": {"text": "Found 14 console/debugger/print-style debug statements in non-test source. This is a common fast-generation residue before production cleanup."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "low", "confidence": 1.0}}, {"id": "scanner-72b2a6250083a784", "name": "Placeholder or mock-heavy implementation detected", "shortDescription": {"text": "Placeholder or mock-heavy implementation detected"}, "fullDescription": {"text": "Found 12 placeholder/mock markers across 4 source files. This often means the repo looks complete while core flows still use generated scaffolding or fake data."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}, {"id": "scanner-2d0c7b7ab8f8aacf", "name": "Critical user flow still appears backed by mock or placeholder data", "shortDescription": {"text": "Critical user flow still appears backed by mock or placeholder data"}, "fullDescription": {"text": "A payment/auth/admin/order/billing-style flow contains mock, fake, TODO, dummy, or placeholder markers in runtime source. In the Fable corpus this is a high-leverage completeness smell: the app can look finished while the money, identity, or tenant flow is still scaffolded."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}, {"id": "scanner-b9088664ace7f748", "name": "Composite production-readiness gap", "shortDescription": {"text": "Composite production-readiness gap"}, "fullDescription": {"text": "Multiple low-cost hardening controls are missing together: ci, tests. Opus verification showed these co-occurring gaps are a better readiness signal than reading each flag in isolation."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "low", "confidence": 1.0}}, {"id": "scanner-749d4bc1bd66df5f", "name": "Agent instructions exist but release-hardening basics are missing", "shortDescription": {"text": "Agent instructions exist but release-hardening basics are missing"}, "fullDescription": {"text": "AI-coder instruction files were found, but the repo is missing ci, tests. Treat this as a contract gap: the agent is guided, but the generated output is not yet guarded by the controls that make it repeatable."}, "properties": {"scanner": "scanner-primary", "layer": "quality", "severity": "medium", "confidence": 1.0}}]}}, "automationDetails": {"id": "repobility/3449"}, "properties": {"repository": "asgeirtj/system_prompts_leaks", "repoUrl": "https://github.com/asgeirtj/system_prompts_leaks", "branch": "main"}, "results": [{"ruleId": "scanner-b8263e9f0e19a497", "level": "note", "message": {"text": "Possibly dead Python function: lin2s"}, "properties": {"repobilityId": "6732e1b72514776e", "scanner": "scanner-primary", "fingerprint": "b8263e9f0e19a497", "layer": "software", "severity": "low", "confidence": 1.0, "tags": ["dead-code"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/dataviz/scripts/validate_palette.py:87"}, "region": {"startLine": 1}}}]}, {"ruleId": "scanner-e7496589e2b9ff68", "level": "error", "message": {"text": "Agent instruction/config may expose a secret: Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "properties": {"repobilityId": "855431f514fbdd31", "scanner": "scanner-primary", "fingerprint": "e7496589e2b9ff68", "layer": "security", "severity": "high", "confidence": 1.0, "tags": ["agent-instructions", "secrets", "skill_file"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "region": {"startLine": 291}}}]}, {"ruleId": "scanner-72eb7e7dc8d20e9e", "level": "warning", "message": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md"}, "properties": {"repobilityId": "5eaccb9a1e0d1227", "scanner": "scanner-primary", "fingerprint": "72eb7e7dc8d20e9e", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["agent-instructions", "verification", "skill_file"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md"}, "region": {"startLine": 1}}}]}, {"ruleId": "scanner-9e35e425c83c8ed7", "level": "warning", "message": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "properties": {"repobilityId": "f891adc857aa66ed", "scanner": "scanner-primary", "fingerprint": "9e35e425c83c8ed7", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["agent-instructions", "verification", "skill_file"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "region": {"startLine": 1}}}]}, {"ruleId": "scanner-2f25281023ac0841", "level": "warning", "message": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/design-sync/storybook/SKILL.md"}, "properties": {"repobilityId": "22da3b326b1acb48", "scanner": "scanner-primary", "fingerprint": "2f25281023ac0841", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["agent-instructions", "verification", "skill_file"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/storybook/SKILL.md"}, "region": {"startLine": 1}}}]}, {"ruleId": "scanner-b0dd92c2e032f924", "level": "warning", "message": {"text": "Agent authority lacks a verifier contract: Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "properties": {"repobilityId": "79a275f4c15cc498", "scanner": "scanner-primary", "fingerprint": "b0dd92c2e032f924", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["agent-instructions", "verification", "skill_file"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "region": {"startLine": 1}}}]}, {"ruleId": "scanner-44533f9ddb4bf0fa", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/curl/examples.md"}, "properties": {"repobilityId": "1a44fd2d32304ce2", "scanner": "scanner-primary", "fingerprint": "44533f9ddb4bf0fa", "layer": "security", "severity": "medium", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/curl/examples.md"}, "region": {"startLine": 1}}}]}, {"ruleId": "scanner-26d29b77d20cfd9f", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/curl/managed-agents.md"}, "properties": {"repobilityId": "7934b594ab58270a", "scanner": "scanner-primary", "fingerprint": "26d29b77d20cfd9f", "layer": "security", "severity": "medium", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/curl/managed-agents.md"}, "region": {"startLine": 1}}}]}, {"ruleId": "scanner-5142746dd2d3c7c2", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/go/managed-agents/README.md"}, "properties": {"repobilityId": "c4e8e562cdbc8ea3", "scanner": "scanner-primary", "fingerprint": "5142746dd2d3c7c2", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/go/managed-agents/README.md"}, "region": {"startLine": 392}}}]}, {"ruleId": "scanner-4e1f87d29758252e", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/java/managed-agents/README.md"}, "properties": {"repobilityId": "c7fe1ec18fa4b94d", "scanner": "scanner-primary", "fingerprint": "4e1f87d29758252e", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/java/managed-agents/README.md"}, "region": {"startLine": 303}}}]}, {"ruleId": "scanner-78d5a466fa906fff", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/php/managed-agents/README.md"}, "properties": {"repobilityId": "1aa8d1244d91b448", "scanner": "scanner-primary", "fingerprint": "78d5a466fa906fff", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/php/managed-agents/README.md"}, "region": {"startLine": 214}}}]}, {"ruleId": "scanner-8e9d1a862f7cee1a", "level": "error", "message": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md"}, "properties": {"repobilityId": "f02c84aeae5079d8", "scanner": "scanner-primary", "fingerprint": "8e9d1a862f7cee1a", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "data-exfil", "E4"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md"}, "region": {"startLine": 331}}}]}, {"ruleId": "scanner-787eb51095d30365", "level": "error", "message": {"text": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/python/managed-agents/README.md"}, "properties": {"repobilityId": "1b89f8f6e266391f", "scanner": "scanner-primary", "fingerprint": "787eb51095d30365", "layer": "security", "severity": "high", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "data-exfil", "E2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/python/managed-agents/README.md"}, "region": {"startLine": 102}}}]}, {"ruleId": "scanner-d11397e135f76617", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/ruby/managed-agents/README.md"}, "properties": {"repobilityId": "28d4f2848d360e3e", "scanner": "scanner-primary", "fingerprint": "d11397e135f76617", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/ruby/managed-agents/README.md"}, "region": {"startLine": 273}}}]}, {"ruleId": "scanner-0224924703c756a4", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "properties": {"repobilityId": "d6cc2f9308670fee", "scanner": "scanner-primary", "fingerprint": "0224924703c756a4", "layer": "security", "severity": "medium", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "region": {"startLine": 58}}}]}, {"ruleId": "scanner-159db39500b4a4ce", "level": "error", "message": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/live-sources.md"}, "properties": {"repobilityId": "00c6e26ae7230f88", "scanner": "scanner-primary", "fingerprint": "159db39500b4a4ce", "layer": "security", "severity": "high", "confidence": 0.75, "tags": ["skillspector", "mcp-skill", "data-exfil", "E4"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/live-sources.md"}, "region": {"startLine": 73}}}]}, {"ruleId": "scanner-28ea41bc622ec69a", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-api-reference.md"}, "properties": {"repobilityId": "0c26c04813c99c4b", "scanner": "scanner-primary", "fingerprint": "28ea41bc622ec69a", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-api-reference.md"}, "region": {"startLine": 251}}}]}, {"ruleId": "scanner-5e510ebf6dbc9b26", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "properties": {"repobilityId": "987e3abf6a35a0ee", "scanner": "scanner-primary", "fingerprint": "5e510ebf6dbc9b26", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "region": {"startLine": 149}}}]}, {"ruleId": "scanner-cd7a8253f49692e8", "level": "error", "message": {"text": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "properties": {"repobilityId": "7973428790449fd1", "scanner": "scanner-primary", "fingerprint": "cd7a8253f49692e8", "layer": "security", "severity": "high", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "data-exfil", "E2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "region": {"startLine": 200}}}]}, {"ruleId": "scanner-1ba28e1d7f8b652c", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-scheduled-deployments.md"}, "properties": {"repobilityId": "5a7e03aa7476a7c7", "scanner": "scanner-primary", "fingerprint": "1ba28e1d7f8b652c", "layer": "security", "severity": "medium", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-scheduled-deployments.md"}, "region": {"startLine": 16}}}]}, {"ruleId": "scanner-9e6b1a1450328661", "level": "error", "message": {"text": "SkillSpector E2 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-self-hosted-sandboxes.md"}, "properties": {"repobilityId": "85b02aa2f89f8053", "scanner": "scanner-primary", "fingerprint": "9e6b1a1450328661", "layer": "security", "severity": "high", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "data-exfil", "E2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-self-hosted-sandboxes.md"}, "region": {"startLine": 40}}}]}, {"ruleId": "scanner-8f336bada82af29d", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "properties": {"repobilityId": "7fde1d47b8269702", "scanner": "scanner-primary", "fingerprint": "8f336bada82af29d", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "region": {"startLine": 236}}}]}, {"ruleId": "scanner-057305514468c795", "level": "error", "message": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md"}, "properties": {"repobilityId": "a23896648117efe3", "scanner": "scanner-primary", "fingerprint": "057305514468c795", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "data-exfil", "E4"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md"}, "region": {"startLine": 1172}}}]}, {"ruleId": "scanner-98a5e8748ede1724", "level": "warning", "message": {"text": "SkillSpector E1 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/shared/models.md"}, "properties": {"repobilityId": "71853bc26d3fa15f", "scanner": "scanner-primary", "fingerprint": "98a5e8748ede1724", "layer": "security", "severity": "medium", "confidence": 0.5, "tags": ["skillspector", "mcp-skill", "data-exfil", "E1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/models.md"}, "region": {"startLine": 35}}}]}, {"ruleId": "scanner-5525aaa724037c51", "level": "error", "message": {"text": "SkillSpector E4 (data-exfil) in Anthropic/Claude Code/bundled-skills/claude-api/typescript/claude-api/README.md"}, "properties": {"repobilityId": "2ccb96e90a70e2a2", "scanner": "scanner-primary", "fingerprint": "5525aaa724037c51", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "data-exfil", "E4"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/typescript/claude-api/README.md"}, "region": {"startLine": 253}}}]}, {"ruleId": "scanner-37bf457f31be4e3f", "level": "note", "message": {"text": "SkillSpector EA3 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/LICENSE.txt"}, "properties": {"repobilityId": "0c6b4f23fa5382e0", "scanner": "scanner-primary", "fingerprint": "37bf457f31be4e3f", "layer": "security", "severity": "low", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/LICENSE.txt"}, "region": {"startLine": 28}}}]}, {"ruleId": "scanner-a88831714e0bcf71", "level": "warning", "message": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "properties": {"repobilityId": "d59fe4e1c3678316", "scanner": "scanner-primary", "fingerprint": "a88831714e0bcf71", "layer": "security", "severity": "medium", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "region": {"startLine": 208}}}]}, {"ruleId": "scanner-eea1aebc8055f343", "level": "warning", "message": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/go/claude-api/tool-use.md"}, "properties": {"repobilityId": "e4d3daae22317d74", "scanner": "scanner-primary", "fingerprint": "eea1aebc8055f343", "layer": "security", "severity": "medium", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/go/claude-api/tool-use.md"}, "region": {"startLine": 42}}}]}, {"ruleId": "scanner-302bb8e3fbe179a0", "level": "warning", "message": {"text": "SkillSpector EA4 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md"}, "properties": {"repobilityId": "bace4139288ad787", "scanner": "scanner-primary", "fingerprint": "302bb8e3fbe179a0", "layer": "security", "severity": "medium", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA4"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/README.md"}, "region": {"startLine": 57}}}]}, {"ruleId": "scanner-f3cf9348a037f9a4", "level": "warning", "message": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/tool-use.md"}, "properties": {"repobilityId": "e6e2b478395d5b5b", "scanner": "scanner-primary", "fingerprint": "f3cf9348a037f9a4", "layer": "security", "severity": "medium", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/python/claude-api/tool-use.md"}, "region": {"startLine": 28}}}]}, {"ruleId": "scanner-c22abd8be8160863", "level": "warning", "message": {"text": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md"}, "properties": {"repobilityId": "55f59acc0621d2fc", "scanner": "scanner-primary", "fingerprint": "c22abd8be8160863", "layer": "security", "severity": "medium", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md"}, "region": {"startLine": 26}}}]}, {"ruleId": "scanner-bf624f267c277a6f", "level": "warning", "message": {"text": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "properties": {"repobilityId": "e2f39474c236d549", "scanner": "scanner-primary", "fingerprint": "bf624f267c277a6f", "layer": "security", "severity": "medium", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "region": {"startLine": 210}}}]}, {"ruleId": "scanner-b44886185b845395", "level": "warning", "message": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md"}, "properties": {"repobilityId": "8ce59f1a7da68bad", "scanner": "scanner-primary", "fingerprint": "b44886185b845395", "layer": "security", "severity": "medium", "confidence": 0.75, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/model-migration.md"}, "region": {"startLine": 1228}}}]}, {"ruleId": "scanner-3f9963f15766966c", "level": "warning", "message": {"text": "SkillSpector EA1 (excessive-agency) in Anthropic/Claude Code/bundled-skills/claude-api/shared/tool-use-concepts.md"}, "properties": {"repobilityId": "b621b0abd44af6d2", "scanner": "scanner-primary", "fingerprint": "3f9963f15766966c", "layer": "security", "severity": "medium", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/tool-use-concepts.md"}, "region": {"startLine": 82}}}]}, {"ruleId": "scanner-619f6af183c80d8d", "level": "warning", "message": {"text": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "properties": {"repobilityId": "3fa4606c24009ea6", "scanner": "scanner-primary", "fingerprint": "619f6af183c80d8d", "layer": "security", "severity": "medium", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "memory-poisoning", "MP2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "region": {"startLine": 468}}}]}, {"ruleId": "scanner-d5587e0c0da5465e", "level": "warning", "message": {"text": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md"}, "properties": {"repobilityId": "4c9f9a4ab53e4735", "scanner": "scanner-primary", "fingerprint": "d5587e0c0da5465e", "layer": "security", "severity": "medium", "confidence": 0.8, "tags": ["skillspector", "mcp-skill", "memory-poisoning", "MP2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/agent-design.md"}, "region": {"startLine": 80}}}]}, {"ruleId": "scanner-ccf41afaf901fa58", "level": "warning", "message": {"text": "SkillSpector PE2 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "properties": {"repobilityId": "eb37788bd25786e1", "scanner": "scanner-primary", "fingerprint": "ccf41afaf901fa58", "layer": "security", "severity": "medium", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "region": {"startLine": 25}}}]}, {"ruleId": "scanner-0a6621bdd81ce15e", "level": "error", "message": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "properties": {"repobilityId": "bdd1c4182c7b1b90", "scanner": "scanner-primary", "fingerprint": "0a6621bdd81ce15e", "layer": "security", "severity": "high", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "region": {"startLine": 65}}}]}, {"ruleId": "scanner-ebc829283a442ba5", "level": "error", "message": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "properties": {"repobilityId": "475f25fbd5c92090", "scanner": "scanner-primary", "fingerprint": "ebc829283a442ba5", "layer": "security", "severity": "high", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-environments.md"}, "region": {"startLine": 128}}}]}, {"ruleId": "scanner-d75a07facc8588c3", "level": "error", "message": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "properties": {"repobilityId": "f102f84f13e46329", "scanner": "scanner-primary", "fingerprint": "d75a07facc8588c3", "layer": "security", "severity": "high", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/managed-agents-tools.md"}, "region": {"startLine": 214}}}]}, {"ruleId": "scanner-304ef16ce4a64286", "level": "warning", "message": {"text": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "properties": {"repobilityId": "c5d20daffed3924a", "scanner": "scanner-primary", "fingerprint": "304ef16ce4a64286", "layer": "security", "severity": "medium", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "rogue-agent", "RA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/SKILL.md"}, "region": {"startLine": 193}}}]}, {"ruleId": "scanner-831a5338262cba55", "level": "error", "message": {"text": "SkillSpector TM2 (tool-misuse) in Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "properties": {"repobilityId": "3fedab52520a52ea", "scanner": "scanner-primary", "fingerprint": "831a5338262cba55", "layer": "security", "severity": "high", "confidence": 0.75, "tags": ["skillspector", "mcp-skill", "tool-misuse", "TM2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/claude-api/shared/anthropic-cli.md"}, "region": {"startLine": 25}}}]}, {"ruleId": "scanner-b5524b9516d07605", "level": "warning", "message": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/design-sync/lib/sync-hashes.mjs"}, "properties": {"repobilityId": "3608afcd21e96480", "scanner": "scanner-primary", "fingerprint": "b5524b9516d07605", "layer": "security", "severity": "medium", "confidence": 0.75, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/lib/sync-hashes.mjs"}, "region": {"startLine": 100}}}]}, {"ruleId": "scanner-c824c1a6f3e019eb", "level": "warning", "message": {"text": "SkillSpector EA2 (excessive-agency) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "properties": {"repobilityId": "4e438f12eea1f90d", "scanner": "scanner-primary", "fingerprint": "c824c1a6f3e019eb", "layer": "security", "severity": "medium", "confidence": 0.75, "tags": ["skillspector", "mcp-skill", "excessive-agency", "EA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "region": {"startLine": 20}}}]}, {"ruleId": "scanner-4f6ecd5bbbb7d38d", "level": "error", "message": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/design-sync/lib/common.mjs"}, "properties": {"repobilityId": "277aa6ca3e25bf68", "scanner": "scanner-primary", "fingerprint": "4f6ecd5bbbb7d38d", "layer": "security", "severity": "high", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/lib/common.mjs"}, "region": {"startLine": 141}}}]}, {"ruleId": "scanner-4f70436aa882c705", "level": "error", "message": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs"}, "properties": {"repobilityId": "c981c16ddf536c9b", "scanner": "scanner-primary", "fingerprint": "4f70436aa882c705", "layer": "security", "severity": "high", "confidence": 0.6, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs"}, "region": {"startLine": 11}}}]}, {"ruleId": "scanner-eff36cca435ff1cc", "level": "error", "message": {"text": "SkillSpector P2 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/lib/emit.mjs"}, "properties": {"repobilityId": "4ad387d481b62fa5", "scanner": "scanner-primary", "fingerprint": "eff36cca435ff1cc", "layer": "security", "severity": "high", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "prompt-injection", "P2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/lib/emit.mjs"}, "region": {"startLine": 128}}}]}, {"ruleId": "scanner-5f40c16936ca76dc", "level": "error", "message": {"text": "SkillSpector P2 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "properties": {"repobilityId": "6021ee6e22707aba", "scanner": "scanner-primary", "fingerprint": "5f40c16936ca76dc", "layer": "security", "severity": "high", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "prompt-injection", "P2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "region": {"startLine": 93}}}]}, {"ruleId": "scanner-2201a0896e408b97", "level": "warning", "message": {"text": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md"}, "properties": {"repobilityId": "18ce312bb347beaa", "scanner": "scanner-primary", "fingerprint": "2201a0896e408b97", "layer": "security", "severity": "medium", "confidence": 0.75, "tags": ["skillspector", "mcp-skill", "rogue-agent", "RA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/SKILL.md"}, "region": {"startLine": 62}}}]}, {"ruleId": "scanner-afa7315cb5586e47", "level": "warning", "message": {"text": "SkillSpector RA2 (rogue-agent) in Anthropic/Claude Code/bundled-skills/design-sync/lib/source-kit.mjs"}, "properties": {"repobilityId": "3d127862082b88fe", "scanner": "scanner-primary", "fingerprint": "afa7315cb5586e47", "layer": "security", "severity": "medium", "confidence": 0.75, "tags": ["skillspector", "mcp-skill", "rogue-agent", "RA2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/lib/source-kit.mjs"}, "region": {"startLine": 9}}}]}, {"ruleId": "scanner-c7f1e67f3033ee2b", "level": "error", "message": {"text": "SkillSpector P6 (prompt-injection) in Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs"}, "properties": {"repobilityId": "1b5992fd8bcea234", "scanner": "scanner-primary", "fingerprint": "c7f1e67f3033ee2b", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "prompt-injection", "P6"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/lib/css.mjs"}, "region": {"startLine": 48}}}]}, {"ruleId": "scanner-2415a3d8869eef89", "level": "error", "message": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/lib/preview-rebuild.mjs"}, "properties": {"repobilityId": "97279925e125e2dd", "scanner": "scanner-primary", "fingerprint": "2415a3d8869eef89", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "tool-misuse", "TM1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/lib/preview-rebuild.mjs"}, "region": {"startLine": 9}}}]}, {"ruleId": "scanner-c010cc119ae79d23", "level": "error", "message": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "properties": {"repobilityId": "a79d122c2e737060", "scanner": "scanner-primary", "fingerprint": "c010cc119ae79d23", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "tool-misuse", "TM1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/non-storybook/SKILL.md"}, "region": {"startLine": 91}}}]}, {"ruleId": "scanner-260dcb99b8b367ab", "level": "error", "message": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/design-sync/package-build.mjs"}, "properties": {"repobilityId": "5c927e67ab9fdce6", "scanner": "scanner-primary", "fingerprint": "260dcb99b8b367ab", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "tool-misuse", "TM1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/package-build.mjs"}, "region": {"startLine": 190}}}]}, {"ruleId": "scanner-bbdd0c81a4d188cd", "level": "warning", "message": {"text": "SkillSpector MP2 (memory-poisoning) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/playwright.md"}, "properties": {"repobilityId": "b4ff0001a5d0a812", "scanner": "scanner-primary", "fingerprint": "bbdd0c81a4d188cd", "layer": "security", "severity": "medium", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "memory-poisoning", "MP2"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/playwright.md"}, "region": {"startLine": 35}}}]}, {"ruleId": "scanner-61b434bed383a1cb", "level": "error", "message": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "properties": {"repobilityId": "e2f78580d665a5b5", "scanner": "scanner-primary", "fingerprint": "61b434bed383a1cb", "layer": "security", "severity": "high", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "region": {"startLine": 161}}}]}, {"ruleId": "scanner-af04ee15f59f3478", "level": "error", "message": {"text": "SkillSpector PE3 (priv-esc) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "properties": {"repobilityId": "8d6473b57ac5da1d", "scanner": "scanner-primary", "fingerprint": "af04ee15f59f3478", "layer": "security", "severity": "high", "confidence": 0.7, "tags": ["skillspector", "mcp-skill", "priv-esc", "PE3"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "region": {"startLine": 355}}}]}, {"ruleId": "scanner-5eeba6a45ea9a7da", "level": "error", "message": {"text": "SkillSpector RA1 (rogue-agent) in Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "properties": {"repobilityId": "aa3ac8c1505ae082", "scanner": "scanner-primary", "fingerprint": "5eeba6a45ea9a7da", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "rogue-agent", "RA1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/run-skill-generator/SKILL.md"}, "region": {"startLine": 231}}}]}, {"ruleId": "scanner-534fa5305f9624c0", "level": "error", "message": {"text": "SkillSpector RA1 (rogue-agent) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "properties": {"repobilityId": "fbdfcb9ea4d087d5", "scanner": "scanner-primary", "fingerprint": "534fa5305f9624c0", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "rogue-agent", "RA1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "region": {"startLine": 230}}}]}, {"ruleId": "scanner-a7a8f60edcf2216e", "level": "error", "message": {"text": "SkillSpector TM1 (tool-misuse) in Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "properties": {"repobilityId": "8bd1f8945b21b22f", "scanner": "scanner-primary", "fingerprint": "a7a8f60edcf2216e", "layer": "security", "severity": "high", "confidence": 0.85, "tags": ["skillspector", "mcp-skill", "tool-misuse", "TM1"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/run-skill-generator/examples/electron.md"}, "region": {"startLine": 317}}}]}, {"ruleId": "scanner-e637c415447867e4", "level": "none", "message": {"text": "Run SkillSpector's LLM-backed analysis in your own pipeline"}, "properties": {"repobilityId": "1936f198ff5212bf", "scanner": "scanner-primary", "fingerprint": "e637c415447867e4", "layer": "security", "severity": "info", "confidence": 1.0, "tags": ["skillspector", "mcp-skill", "llm-advisory", "ai-coder"]}}, {"ruleId": "scanner-2fb77ce69f44a2a2", "level": "error", "message": {"text": "Insecure pattern 'new_function_used' in Anthropic/Claude Code/bundled-skills/design-sync/package-validate.mjs:65"}, "properties": {"repobilityId": "177cd5bedeadc6f8", "scanner": "scanner-primary", "fingerprint": "2fb77ce69f44a2a2", "layer": "security", "severity": "high", "confidence": 1.0, "tags": ["owasp", "new_function_used"]}, "locations": [{"physicalLocation": {"artifactLocation": {"uri": "Anthropic/Claude Code/bundled-skills/design-sync/package-validate.mjs"}, "region": {"startLine": 65}}}]}, {"ruleId": "scanner-4ff4adf982755127", "level": "note", "message": {"text": "Very large file: Anthropic/Claude Code/bundled-skills/design-sync/package-build.mjs (1005 lines)"}, "properties": {"repobilityId": "77c2609252fcffc2", "scanner": "scanner-primary", "fingerprint": "4ff4adf982755127", "layer": "quality", "severity": "low", "confidence": 1.0, "tags": ["complexity"]}}, {"ruleId": "scanner-63d60c4fae83e340", "level": "note", "message": {"text": "Very large file: Anthropic/Claude Code/bundled-skills/design-sync/package-validate.mjs (804 lines)"}, "properties": {"repobilityId": "265d272e102862ca", "scanner": "scanner-primary", "fingerprint": "63d60c4fae83e340", "layer": "quality", "severity": "low", "confidence": 1.0, "tags": ["complexity"]}}, {"ruleId": "scanner-6893a6c8b0861585", "level": "warning", "message": {"text": "Very low test-to-source ratio"}, "properties": {"repobilityId": "54a7de3f06314bf0", "scanner": "scanner-primary", "fingerprint": "6893a6c8b0861585", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["tests", "coverage"]}}, {"ruleId": "scanner-3ab5d313dda8e5f9", "level": "note", "message": {"text": "Debug logging residue appears in source files"}, "properties": {"repobilityId": "68cd20e3a9618ea7", "scanner": "scanner-primary", "fingerprint": "3ab5d313dda8e5f9", "layer": "quality", "severity": "low", "confidence": 1.0, "tags": ["debug", "cleanup", "repo-hardening", "generated-repo-pattern"]}}, {"ruleId": "scanner-72b2a6250083a784", "level": "warning", "message": {"text": "Placeholder or mock-heavy implementation detected"}, "properties": {"repobilityId": "f962483f00fabd6c", "scanner": "scanner-primary", "fingerprint": "72b2a6250083a784", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["placeholder", "mock-data", "incomplete", "generated-repo-pattern"]}}, {"ruleId": "scanner-2d0c7b7ab8f8aacf", "level": "warning", "message": {"text": "Critical user flow still appears backed by mock or placeholder data"}, "properties": {"repobilityId": "baeec35ab1993928", "scanner": "scanner-primary", "fingerprint": "2d0c7b7ab8f8aacf", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["placeholder", "mock-data", "critical-flow", "generated-repo-pattern"]}}, {"ruleId": "scanner-b9088664ace7f748", "level": "note", "message": {"text": "Composite production-readiness gap"}, "properties": {"repobilityId": "58a01b1954dc0404", "scanner": "scanner-primary", "fingerprint": "b9088664ace7f748", "layer": "quality", "severity": "low", "confidence": 1.0, "tags": ["production-readiness", "repo-hardening", "generated-repo-pattern"]}}, {"ruleId": "scanner-749d4bc1bd66df5f", "level": "warning", "message": {"text": "Agent instructions exist but release-hardening basics are missing"}, "properties": {"repobilityId": "49cc10d41211c79c", "scanner": "scanner-primary", "fingerprint": "749d4bc1bd66df5f", "layer": "quality", "severity": "medium", "confidence": 1.0, "tags": ["agent-instructions", "repo-hardening", "generated-repo-pattern"]}}]}]}