ClawAudit verdict

zero-token

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

The skill routes agent traffic through a third-party aggregator gateway (Free-Way) and uses an opaque '::GENE{}/::DNA{}' behavioral injection syntax to override agent personality and decision logic, which is an unusual level of behavioral control beyond a simple fallback mechanism.

⚠ 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.

90
security
90
transparency
90
maintenance

Findings (1)

Pattern match medium

Instructs covert action — may act without user awareness

SOUL.md · prose · downgraded · quietly

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