verification
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s stated purpose matches code review and QA, but its footprint is broader than a simple verifier because it can autonomously edit code in a loop and delegates key behavior to unspecified transitive skills. No clear credential theft, exfiltration endpoint, or malicious installer is present; risk is mainly from autonomous modification and unverifiable delegated behavior.
Confidence: 84%Severity: 63%
Audit Metadata