ClawAudit verdict

liewatch

skill-liewatch

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

The skill plays the LIE.WATCH AI social deduction game. No malicious behavior detected.

⚠ 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.

73
security
70
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match medium

Opens WebSocket connection

SKILL.md · code · WebSocket

Pattern match medium

Instructs covert action — may act without user awareness

connector.js · prose · downgraded · silently

Pattern match low

Accesses sensitive environment variables

connector.js · prose · downgraded · process.env.PLATFORM_KEY

Permissions & capabilities

Requires 2 environment variables.

package_installnetwork_in

Is this flag fair?

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