ClawAudit verdict
signet-guardian
The skill seems to be a legitimate payment guard middleware for AI agents, providing a policy firewall for money actions.
⚠ 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)
Accesses OpenClaw config/secrets directly
docs/DASHBOARD_TEST.md · prose · downgraded · ~/.openclaw/openclaw.json
HTTP request to bare IP address — common in malicious payloads
README.md · prose · downgraded · http://127.0.0.1
References child_process — can spawn system processes
scripts/signet-cli.ts · prose · downgraded · child_process
Popular HTTP library — network access
test-guardian.sh · prose · downgraded · Got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.