code-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown text defining a persona and instructions. It does not contain any executable scripts, binaries, or automated shell commands.\n- [PROMPT_INJECTION]: The skill is designed to analyze third-party code, which presents a surface for indirect prompt injection where malicious instructions could be embedded in code comments.\n
- Ingestion points: External code snippets and files provided by users for review.\n
- Boundary markers: Absent. The instructions do not define delimiters to isolate untrusted code from the agent's internal logic.\n
- Capability inventory: No executable capabilities or system-level access are requested by the skill's own text.\n
- Sanitization: No sanitization or validation logic is provided for the input code content.
Audit Metadata