owasp-security-code-review
Warn
Audited by Socket on Sep 3, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is coherent and uses official OWASP reference sources, with no install-trust or credential-routing problems. However, it equips an AI agent to perform security review and generate PoC scripts against untrusted code, which is a high-risk offensive capability and creates indirect prompt-injection exposure despite otherwise proportionate scope.
Confidence: 89%Severity: 74%
Audit Metadata