ClawAudit verdict
skill-creator
jpeng-skill-creator
The skill has the dynamic_eval capability, which can be used to execute arbitrary code. However, the skill's description and usage suggest that it is intended for legitimate purposes.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
Instructs covert action โ may act without user awareness
SKILL.md ยท prose ยท downgraded ยท without telling
Popular HTTP library โ network access
SKILL.md ยท prose ยท downgraded ยท got
Permissions & capabilities
No declared permissions โ minimal attack surface.
dynamic_eval Is this flag fair?
Thanks โ recorded.