ClawAudit verdict
humanize-skill
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.
Findings (3)
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
Instructs covert action — may act without user awareness
docs/detection-aware-methods.md · prose · downgraded · silently
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?
Thanks — recorded.