security-reviewer

Warn

Audited by Socket on Mar 24, 2026

1 alert found:

Security
SecurityMEDIUM
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
Analyzed At
Mar 24, 2026, 10:33 AM
Package URL
pkg:socket/skills-sh/jeffallan%2Fclaude-skills%2Fsecurity-reviewer%2F@c18236ee914c1de8a3d83a3d503af579b2aa7f16