Caveat verdict

self-heal-watchdog

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Self-healing watchdog for OpenClaw gateway with process monitoring and model failover; logs only to localhost, does not log API keys, only restarts local processes.

⚠ 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.

60
security
70
transparency
70
maintenance

Findings (2)

Pattern match critical

Recursive delete from root or home — destructive command

README.md · code · rm -rf ~

Pattern match medium

Accesses OpenClaw config/secrets directly

SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json

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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API