unfreeze
Warn
Audited by Socket on Mar 28, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally coherent but its stated purpose is to disable an existing safety mechanism by removing path-boundary restrictions. There is no exfiltration or supply-chain behavior, yet the local state change weakens protections and materially increases downstream agent access.
Confidence: 94%Severity: 88%
Audit Metadata