ClawAudit verdict
skill_guard
skill-guard-waai
Security scanner defining risk pattern categories with Python scanning utilities; the risk patterns are detection logic documentation not 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 (8)
Uses eval() — can execute arbitrary code
skill_guard.py · prose · downgraded · eval(
Accesses sensitive system files
skill_guard.py · prose · downgraded · /etc/passwd
Uses exec() — may execute shell commands
skill_guard.py · prose · downgraded · exec(
Accesses shell history/config
skill_guard.py · prose · downgraded · ~/.bash_history
References sudo — requests elevated privileges
skill_guard.py · prose · downgraded · sudo
setuid — privilege escalation mechanism
skill_guard.py · prose · downgraded · setuid
Opens WebSocket connection
skill_guard.py · prose · downgraded · websocket
Sets world-executable permissions
skill_guard.py · prose · downgraded · chmod 777
Permissions & capabilities
Requires 1 system binary.
Is this flag fair?
Thanks — recorded.