code-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- SAFE (SAFE): The skill is a set of guidelines for code reviews. It does not include commands for network access, file system manipulation, or credential harvesting.
- NO_CODE (SAFE): No scripts, binaries, or external dependencies are associated with this skill, which significantly minimizes the potential attack surface.
- Indirect Prompt Injection (SAFE): Although the skill is designed to process untrusted code, it lacks exploitable capabilities like command execution or file-writing that would allow an attacker to gain persistence or exfiltrate data.
Audit Metadata