ClawAudit verdict
tommo-skill-guard
This is a read-only security scanner that explicitly uses a zero-exec approach via the built-in read tool to scan skill files for dangerous patterns; it performs ClawHub lookups and local pattern matching without executing any code, fully matching its stated security scanning purpose.
⚠ 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 (9)
Uses eval() — can execute arbitrary code
SKILL.md · prose · downgraded · eval(
Pipe to python — executes piped content as Python code
references/security-patterns.md · prose · downgraded · | Python
Uses exec() — may execute shell commands
SKILL.md · prose · downgraded · exec(
References child_process — can spawn system processes
SKILL.md · prose · downgraded · child_process
Base64 decode (atob) — may hide malicious payloads
references/security-patterns.md · prose · downgraded · atob(
References sudo — requests elevated privileges
references/security-patterns.md · prose · downgraded · sudo
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Popular HTTP library — network access
references/security-patterns.md · prose · downgraded · axios
Sets world-executable permissions
references/security-patterns.md · prose · downgraded · chmod 777
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.