tool-mastery
Warn
Audited by Socket on Sep 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
This is a coherent offensive-security skill, not a disguised exfiltration lure, but it gives an AI agent high-risk penetration-testing and defense-evasion capabilities. No clear malware or credential-harvesting data flow is present, yet the offensive scope, broad tool permissions, and exploit guidance make it a high-risk vulnerable skill rather than benign.
Confidence: 91%Severity: 88%
Audit Metadata