ClawAudit verdict
silas_skill_auditor
silas-skill-auditor
A security auditing skill teaching the agent to scan other skills for malicious patterns; the executionSinkDetected flag reflects documented example bash commands for scanning, and the skill itself contains no exfiltration or manipulation.
⚠ 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)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Uses eval() — can execute arbitrary code
SKILL.md · prose · downgraded · eval(
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
References child_process — can spawn system processes
SKILL.md · prose · downgraded · child_process
References sudo — requests elevated privileges
SKILL.md · prose · downgraded · sudo
setuid — privilege escalation mechanism
SKILL.md · prose · downgraded · setuid
Sets world-executable permissions
SKILL.md · prose · downgraded · chmod 777
Opens WebSocket connection
SKILL.md · prose · downgraded · WebSocket
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.