Caveat verdict

improvement-gate

auto-improvement-gate

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

7-layer quality gate for skill improvements that validates candidates against schema, compile, lint, regression, review, doubt, and human-review checks using local scripts; dynamic_eval capability supports the legitimate gating purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

98
security
100
transparency
90
maintenance

Findings (1)

Pattern match low

Popular HTTP library — network access

scripts/review.py · prose · downgraded · got

Permissions & capabilities

No declared permissions — minimal attack surface.

dynamic_eval

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API