secure-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust security methodology for static analysis based on established frameworks (OWASP ASVS, CWE Top 25, OWASP Top 10).
- [SAFE]: Includes a dedicated 'Prompt Injection Safety Notice' that explicitly instructs the agent to treat reviewed code as untrusted, inert text and to ignore any directives embedded in comments or strings, providing a strong defense against indirect prompt injection.
- [SAFE]: The execution environment is restricted to read-only tools (
Read,Grep,Glob), ensuring the skill cannot modify the filesystem or exfiltrate data. - [SAFE]: All external references point to authoritative security resources from trusted organizations, including OWASP, Mitre (CWE), NIST, and Microsoft.
- [SAFE]: Documentation includes clear vulnerable-and-remediated code pairs across multiple languages, serving as a secure knowledge base for the agent without introducing executable risks.
Audit Metadata