ClawAudit verdict
skill-creator
phy-skill-creator
The skill creates new skills and iteratively improves them using dynamic evaluation. While the intent is legitimate, this capability could potentially be used to execute malicious code.
⚠ 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
skill-card.md · prose · downgraded · SKILL.md drafts, eval metadata, benchmark summaries, feedback files, and static
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · without telling
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
dynamic_eval Is this flag fair?
Thanks — recorded.