mattpocock/skills — Repobility public scan

Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.

Sign up free Scan another repo

mattpocock/skills

https://github.com/mattpocock/skills · scanned 2026-07-23 10:41 UTC (5 days, 7 hours ago) · 10 languages

37 raw signals (3 security + 34 graph) 9th percentile · Unknown ·

File as issue Image

UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 5 days, 7 hours ago · v4 · last Δ +27.1 (diff) · 36 actionable findings from 2 signal sources. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON

Security checks

60.0% cov · 34 findings

click to filter

Score breakdown â 2026-05-14-v3

Component	Sub-score	Weight	Contribution
`structure_score`	45.0	0.15	6.75
`security_score`	100.0	0.25	25.00
`testing_score`	0.0	0.20	0.00
`documentation_score`	60.0	0.15	9.00
`practices_score`	30.0	0.15	4.50
`code_quality`	80.0	0.10	8.00
Overall		1.00	53.2

Severity distribution — click a segment to filter

Active filters: excluding tests × Reset all

Severity: Critical 0 High 4 Medium 29 Low 0 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 2 System graph 34 Crowd 0 Layer: Quality 24 Security 7 Cicd 2 Dependencies 3

Exclude dismissed / FP Exclude test files

Corpus Intelligence Cross-corpus context (cohort percentile, top patterns, fix plan) is shown only on repositories you own. Sign up and connect your repo to view it.

Scan summary Repository scanned at 64.1/100 with 60.0% coverage. It contains 316 nodes across 0 cross-layer flows, written primarily in mixed languages. Engine surfaced 34 findings — concentrated in quality (22), security (7), dependencies (3). Risk profile is high: 0 critical, 4 high, 28 medium. Recommended next step: open the quality layer findings first — that's where the highest-impact wins live.

Showing 33 of 36 actionable findings. Click TP / FP to vote on a finding's accuracy — votes adjust the confidence weighting and improve detection across the platform.

high System graph security Skillspector conf 0.85 SkillSpector P6 (prompt-injection) in skills/engineering/diagnosing-bugs/scripts/hitl-loop.template.sh

show instruction Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties. Skill: diagnosing-bugs Rule: P6 Category: prompt-injection Severity: HIGH Confidence: 0.85 Remediation: Remove any instructions that reve…

skills/engineering/diagnosing-bugs/scripts/hitl-loop.template.sh:10 Mcp skillPrompt injectionP6

high System graph security Skillspector conf 0.70 SkillSpector TM2 (tool-misuse) in skills/engineering/to-tickets/SKILL.md

First expand: add the new form beside the old so nothing breaks. Then migrate the call sites over in batches sized by blast radius (per package, per directory), each batch its own ticket blocked by th Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what an…

skills/engineering/to-tickets/SKILL.md:40 Mcp skillTool misuseTm2

high System graph dependencies dependencies conf 0.90 Vulnerable dependency js-yaml 3.14.2: GHSA-52cp-r559-cp3m

OSV.dev reports `js-yaml` at version `3.14.2` (resolved in `package-lock.json`) is affected by GHSA-52cp-r559-cp3m (aka CVE-2026-59869). Note: `js-yaml` is a transitive dependency — pulled in by another package, not declared directly in a manifest. js-yaml: YAML merge-key chains can force quadrati…

package-lock.json ScaOsvGhsa 52cp r559 cp3m

high System graph dependencies dependencies conf 0.90 Vulnerable dependency js-yaml 4.2.0: GHSA-52cp-r559-cp3m

OSV.dev reports `js-yaml` at version `4.2.0` (resolved in `package-lock.json`) is affected by GHSA-52cp-r559-cp3m (aka CVE-2026-59869). Note: `js-yaml` is a transitive dependency — pulled in by another package, not declared directly in a manifest. js-yaml: YAML merge-key chains can force quadratic…

package-lock.json ScaOsvGhsa 52cp r559 cp3m

medium Security checks quality Practices conf 1.00 [CFG006] Missing .gitignore: No .gitignore file. Risk of committing secrets and build artifacts.

Add a .gitignore appropriate for your language/framework.

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: CLAUDE.md

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.

CLAUDE.md VerificationClaude instruction

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/deprecated/qa/SKILL.md

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.

skills/deprecated/qa/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/engineering/code-review/SKILL.md

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.

skills/engineering/code-review/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/engineering/diagnosing-bugs/SKILL.md

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.

skills/engineering/diagnosing-bugs/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/engineering/grill-with-docs/SKILL.md

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.

skills/engineering/grill-with-docs/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/engineering/prototype/SKILL.md

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.

skills/engineering/prototype/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/engineering/research/SKILL.md

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.

skills/engineering/research/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/engineering/setup-matt-pocock-skills/SKILL.md

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.

skills/engineering/setup-matt-pocock-skills/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/engineering/tdd/SKILL.md

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.

skills/engineering/tdd/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/in-progress/claude-handoff/SKILL.md

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.

skills/in-progress/claude-handoff/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/in-progress/setup-ts-deep-modules/SKILL.md

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.

skills/in-progress/setup-ts-deep-modules/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/in-progress/writing-beats/SKILL.md

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.

skills/in-progress/writing-beats/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/in-progress/writing-fragments/SKILL.md

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.

skills/in-progress/writing-fragments/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/in-progress/writing-shape/SKILL.md

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.

skills/in-progress/writing-shape/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/misc/setup-pre-commit/SKILL.md

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.

skills/misc/setup-pre-commit/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/personal/obsidian-vault/SKILL.md

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.

skills/personal/obsidian-vault/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/productivity/grill-me/SKILL.md

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.

skills/productivity/grill-me/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent authority lacks a verifier contract: skills/productivity/writing-great-skills/SKILL.md

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.

skills/productivity/writing-great-skills/SKILL.md VerificationSkill file

medium System graph quality Agent instructions conf 1.00 Agent instructions exist but release-hardening basics are missing

AI-coder instruction files were found, but the repo is missing 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.

Repo hardeningGenerated repo pattern

medium System graph quality Tests conf 1.00 CI is configured but no tests are detected

A CI pipeline exists, but the scan found no test files to gate. Opus labeled this generated-code pattern as config theater: release machinery exists, but it has little behavioral signal.

CI/CDConfig theaterRepo hardening

medium System graph cicd CI/CD security conf 1.00 GitHub Action is tag-pinned rather than SHA-pinned

actions/checkout@v4 can move without a code change in this repo. Pin third-party actions to a reviewed 40-character commit SHA.

.github/workflows/release.yml:19 CI/CD securitySupply chainGithub actions

medium System graph cicd CI/CD security conf 1.00 GitHub Actions workflow grants broad write permissions

CI tokens with write permissions increase blast radius when an action, dependency, or PR workflow is compromised. Prefer job-level least-privilege permissions.

.github/workflows/release.yml CI/CD securitySupply chainGithub actions

medium System graph security Coverage conf 1.00 No auth library detected

The scanner did not find any standard auth library (JWT, OAuth, NextAuth, Auth0, etc.). The repo has auth/admin/session surface indicators, so auth may live in custom code, in a separate service, or be missing.

auth

medium System graph security Skillspector conf 0.80 SkillSpector EA2 (excessive-agency) in skills/deprecated/qa/SKILL.md

Do NOT ask the user Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation. Skill: qa Rule: EA2 Category: excessive-agency Severity: MEDIUM …

skills/deprecated/qa/SKILL.md:49 Mcp skillExcessive agencyEa2

medium System graph security Skillspector conf 0.80 SkillSpector EA2 (excessive-agency) in skills/in-progress/batch-grill-me/SKILL.md

don't ask the user Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation. Skill: batch-grill-me Rule: EA2 Category: excessive-agency Severi…

skills/in-progress/batch-grill-me/SKILL.md:13 Mcp skillExcessive agencyEa2

medium System graph security Skillspector conf 0.75 SkillSpector EA2 (excessive-agency) in skills/in-progress/loop-me/SKILL.md

without asking Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation. Skill: loop-me Rule: EA2 Category: excessive-agency Severity: MEDIUM …

skills/in-progress/loop-me/SKILL.md:27 Mcp skillExcessive agencyEa2

medium System graph quality Tests conf 1.00 Very low test-to-source ratio

0 test file(s) for 1 source file(s) (ratio 0.00). Consider adding integration or unit tests for critical paths.

Coverage

medium System graph dependencies dependencies conf 0.90 Vulnerable dependency js-yaml 3.14.2: GHSA-h67p-54hq-rp68

OSV.dev reports `js-yaml` at version `3.14.2` (resolved in `package-lock.json`) is affected by GHSA-h67p-54hq-rp68 (aka CVE-2026-53550). Note: `js-yaml` is a transitive dependency — pulled in by another package, not declared directly in a manifest. JS-YAML: Quadratic-complexity DoS in merge key ha…

package-lock.json ScaOsvGhsa h67p 54hq rp68

For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.

For AI agents + API integrations

Email me when this repo regresses

Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.

API access

This page is publicly accessible at: https://repobility.com/scan/e88c5107-1258-492a-8d47-b0a1e1b3ec1e/

To check status programmatically (no auth required):

curl -s https://repobility.com/api/v1/public/scan/e88c5107-1258-492a-8d47-b0a1e1b3ec1e/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.