security-reviewer
Warn
Audited by Socket on Mar 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally coherent for a security-audit assistant and shows no clear credential theft, covert exfiltration, or deceptive installer behavior. However, it grants an AI agent offensive security and Bash-driven testing capability, which creates high operational risk even with stated authorization constraints.
Confidence: 87%Severity: 74%
Audit Metadata