review-claude
Warn
Audited by Socket on Apr 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is plausible, but the skill achieves it by running unpinned remote third-party code with shell access and likely repo visibility. The main risk is supply-chain and transitive trust, not confirmed malware; the long-running no-interruption instruction further reduces user oversight.
Confidence: 85%Severity: 78%
Audit Metadata