Caveat verdict

multi-agent-status

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

Health monitoring skill for multi-host OpenClaw deployments that pushes JSON status reports to a shared directory; no credentials, no network exfiltration, fully local cross-agent monitoring.

⚠ 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
100
transparency
90
maintenance

Findings (2)

Pattern match critical

Instructs agent to read sensitive file paths

SKILL.md · code · Read all files in /

Pattern match medium

Sets world-executable permissions

SKILL.md · code · chmod 777

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