ClawAudit verdict

openclaw-agency-agents

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill manages and activates AI agent personalities from a repository. While it seems to be for a legitimate purpose, the execution of scripts and cloning of repositories could pose risks if the source is not trusted.

⚠ 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.

100
security
90
transparency
70
maintenance

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