Caveat verdict

skill-craft

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

Evidence-based skill design guide for creating SKILL.md files; meta-skill with no credential access or code execution.

⚠ 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.

18
security
60
transparency
70
maintenance

Findings (5)

Pattern match critical

Instructs agent to hide actions from user

references/skill-optimization.md · code · Do NOT inform the user

Pattern match high

Writes to SKILL.md — self-modifying skill

SKILL.md · prose · downgraded · SKILL.md following all 9 optimization dimensions from the start. Write

Pattern match high

Attempts to modify skills or system prompts

scripts/init_skill.py · prose · downgraded · Edit SKILL.md

Pattern match medium

Popular HTTP library — network access

references/skill-optimization.md · code · axios

Pattern match low

References agent configuration files

references/evidence-database.md · prose · downgraded · CLAUDE.md

Permissions & capabilities

No declared permissions — minimal attack surface.

network_in

Is this flag fair?

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