integrity-forensics
Warn
Audited by Socket on Nov 10, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill’s behavior mostly matches its stated purpose, but it still fetches and executes upstream code and a nested skill from a personal GitHub repository, creating medium supply-chain and transitive-trust risk. No evidence here of credential harvesting, exfiltration, pre-execution payloads, or purpose-incompatible behavior.
Confidence: 87%Severity: 58%
Audit Metadata