ClawAudit verdict

unraid

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Read-only Unraid monitoring skill using a user-provided API key to query the user own local Unraid server via GraphQL; 27 endpoints are all documented as read-only and behavior matches the stated server monitoring purpose.

⚠ 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.

68
security
80
transparency
90
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="your-api-key

Pattern match low

Opens WebSocket connection

references/api-reference.md · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/F). 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.

network_incredential_access

Is this flag fair?

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