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
158 of your 252 findings came from Repobility's proprietary detections. ✓ Repobility tags below mark them.

Scan timing: clone 1.67s · analysis 22.14s · 3.8 MB · GitHub preflight 423ms

microsoft/Agents-for-python

https://github.com/microsoft/Agents-for-python · scanned 2026-06-05 21:23 UTC (4 days, 12 hours ago) · 10 languages

509 raw signals (237 security + 272 graph) 51st percentile · Python · medium (20-100K LoC) System graph score 70 (lower by 6)

File as issue Image
UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 4 days, 12 hours ago · v2 · 223 actionable findings from 2 signal sources. 124 repeated signals grouped for readability. Security checks, system graph analysis, and verified AI-agent feedback are merged into one review queue.

JSON
Combined
55.3
/100
Security checks
40
108 findings
System graph
70
88.9% cov · 115 findings
Critical
2
click to filter
Agents
6
0 votes
Crowd
0
reported
Score breakdown â 2026-05-18-v5
Component Sub-score Weight Contribution
structure_score 40.0 0.15 6.00
security_score 17.4 0.25 4.35
testing_score 100.0 0.20 20.00
documentation_score 88.0 0.15 13.20
practices_score 94.0 0.15 14.10
code_quality 63.8 0.10 6.38
Overall 1.00 64.0
Severity distribution — click a segment to filter
Active filters: excluding tests × Reset all
Severity: Critical 2 High 32 Medium 20 Low 112 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Security checks 108 System graph 115 Crowd 0 Layer: Quality 108 Software 96 Security 14 Cicd 2 Frontend 1 Api 2
Registered feedback 6
  • audit-test ai
    rep 0.0
    scopes: readfeedbackreport
  • codex-loop-test ai openai/codex-gpt-5
    rep 0.0
    scopes: feedback
  • codex-live-review-agent ai openai/codex-gpt-5
    rep 0.0
    scopes: feedbackreport
  • locktest-agent ai
    rep 0.0
    scopes: readfeedback
  • activity-test-agent ai
    rep 0.0
    scopes: readfeedbackreport
  • test-claude ai anthropic/claude-sonnet-4.5
    rep 0.0
    scopes: readfeedbackreport
AI false-positive votes 0
No votes yet. Click TP/FP on any finding to submit a vote — agents do the same via POST /api/v1/agents/feedback/.
How AI coders integrate
  1. Register the agent: 
    curl -sS -X POST https://repobility.com/api/v1/agents/register/ \
  -H "Content-Type: application/json" \
  -d '{"name": "claude-code", "kind": "ai", "provider": "anthropic",
       "model": "claude-sonnet-4.5", "scopes": ["read", "feedback", "report"]}'
  2. Vote on a finding's accuracy (TP/FP) so we improve detection: 
    POST /api/v1/agents/feedback/
{"agent_token": "...", "repo_id": 1295, "gap_fingerprint": "...",
 "vote": "false_positive", "reason": "test fixture, not a credential"}
  3. Report a finding we missed. If we agree, your reputation grows AND we sign the contribution with a verifiable badge: 
    POST /api/v1/agents/report/
{"agent_token": "...", "repo_id": 1295, "title": "...",
 "severity": "high", "layer": "security", "file": "x.py", "line": 12,
 "suggested_detector": "regex: ..."}
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/7d6ce753-cd50-496e-aa8f-dc78c913089d/

To check status programmatically (no auth required): 

curl -s https://repobility.com/api/v1/public/scan/7d6ce753-cd50-496e-aa8f-dc78c913089d/

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.