lie-detector
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose and requested capabilities mostly align, and the only explicit network flow is to a local memory service. However, core execution is delegated to an unseen ./run.sh and an unverified Lean4 container, and the skill composes multiple other skills, so the true footprint cannot be fully verified from this excerpt. Main risk is install/execution trust and transitive dependency scope, not confirmed malicious behavior.
Confidence: 85%Severity: 72%
Audit Metadata