code-review
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a clear and legitimate purpose for reviewing code changes without any suspicious commands or exfiltration patterns.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing untrusted code data.
- Ingestion points: The @$1 argument in SKILL.md receives external code diffs or file content.
- Boundary markers: No explicit delimiters are used to separate the instructions from the untrusted code content.
- Capability inventory: The skill is restricted to file system tools (Read, Glob, Grep) and lacks high-risk tools like code execution or network access.
- Sanitization: The skill does not perform validation or sanitization on the ingested content.
Audit Metadata