Caveat verdict
asf-v4
anfsf-v1
An industrial governance and optimization module (veto checks, ownership proofs, economic scoring) for OpenClaw workflows; executionSinkDetected likely triggered by bash CLI examples which are straightforward local tooling invocations with no credential exfiltration or suspicious behavior.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
Possible hardcoded credential
MANUAL-PUBLISH.md · code · TOKEN="your-api-token
Uses eval() — can execute arbitrary code
PHASE-3-COMPLETE.md · code · eval(
Accesses OpenClaw config/secrets directly
MANUAL-PUBLISH.md · code · ~/.openclaw/openclaw.json
Contains shortened/invite URL
QUICK-WEB-PUBLISH.md · code · discord.gg/clawd
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.