ClawAudit verdict
mayguard
The skill is a security auditor for agent skills, scanning for malicious patterns and providing a safety score.
⚠ 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 (4)
Recursive delete from root or home — destructive command
references/threat_patterns.json · prose · downgraded · rm -rf /
Sets world-executable permissions
references/threat_patterns.json · prose · downgraded · chmod 777
Changes file ownership
references/threat_patterns.json · prose · downgraded · chown
References tunneling service
references/threat_patterns.json · prose · downgraded · ngrok
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.