performing-red-team-with-covenant
Warn
Audited by Socket on Apr 7, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill is internally coherent and uses mostly legitimate same-project install sources, but its purpose is to give an AI agent offensive C2 capability: payload generation, grunt deployment, remote tasking, and lateral movement support. That makes it high risk even without signs of credential theft or deceptive routing.
Confidence: 91%Severity: 88%
Audit Metadata