ClawAudit verdict
integration
88
๐ข Trusted
Low risk โ reviewed by ClawAudit, behavior matches stated purpose
The skill demonstrates basic integration requirements and does not contain any malicious or deceptive behavior. It seems to be used for educational 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.
80
security
60
transparency
50
maintenance
Findings (1)
Pattern match high
Attempts to modify skills or system prompts
README.md ยท prose ยท downgraded ยท Edit SKILL.md
Permissions & capabilities
No declared permissions โ minimal attack surface.
Is this flag fair?
Thanks โ recorded.