ClawAudit verdict
model-failover-guard
Local Python daemon that monitors model health and switches between configured models — behavior matches stated purpose with no suspicious network calls or exfiltration.
⚠ 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 (2)
Accesses OpenClaw config/secrets directly
skills/model-failover-guard/config.example.json · prose · downgraded · ~/.openclaw/openclaw.json
subprocess execution — runs system commands from Python
skills/model-failover-guard/scripts/failover.py · prose · downgraded · subprocess.run(
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.