ClawAudit verdict

humanize-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill's content is focused on improving writing quality and factual grounding, with no evidence of malicious or deceptive behavior.

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

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

68
security
90
transparency
70
maintenance

Findings (3)

Pattern match high

Writes to SKILL.md — self-modifying skill

docs/detection-aware-methods.md · prose · downgraded · SKILL.md` Non-goals and the Boundary in `README.md` apply. Use the main workflow

Pattern match medium

Instructs covert action — may act without user awareness

docs/detection-aware-methods.md · prose · downgraded · silently

Pattern match low

Popular HTTP library — network access

docs/specificity-and-thought.md · prose · downgraded · got

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