decompose
Warn
Audited by Socket on May 12, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally coherent, but its purpose is to equip the agent with high-risk reverse-engineering and security-research capabilities against undocumented/private APIs and LAN devices. Official-tool provenance keeps supply-chain risk moderate, but the combination of sensitive credential capture, active probing, and offensive tooling makes overall security risk high even without evidence of direct credential theft or malicious exfiltration.
Confidence: 90%Severity: 84%
Audit Metadata