Caveat verdict

agent-mesh

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

The skill enables agent-to-agent communication via Supabase, but executionSinkDetected is true, indicating potential risk, and requires careful handling of environment variables.

⚠ 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.

75
security
80
transparency
70
maintenance

Findings (1)

Pattern match high

Instructs covert action — may act without user awareness

SKILL.md · code · silently

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

Requires 3 environment variables. Requires 2 system binaries. (1 elevated: curl).

Is this flag fair?

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