Caveat verdict

skill-forge

auto-skill-forge

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

Generates test suites (task_suite.yaml) and skill definitions (SKILL.md) from existing skills or spec files, operating entirely on local files; a development tooling skill with no network access or data exfiltration.

⚠ 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.

70
security
70
transparency
70
maintenance

Findings (2)

Pattern match high

Writes to SKILL.md — self-modifying skill

tests/test_forge.py · prose · downgraded · SKILL.md").write

Pattern match medium

subprocess execution — runs system commands from Python

scripts/forge.py · prose · downgraded · subprocess.run(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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