code-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection because it processes untrusted data (source code and PR descriptions) without employing defensive boundary markers.\n
- Ingestion points: Data enters the context via the
Read,Grep, andGlobtools used to analyze the codebase and PR descriptions.\n - Boundary markers: The instructions do not specify any delimiters or safety prompts to ensure the agent ignores instructions that might be maliciously embedded within the code comments or PR text it is reviewing.\n
- Capability inventory: The skill is limited to file reading and report generation. It has no capabilities for writing to files, executing code, or making network requests.\n
- Sanitization: There is no evidence of input validation or sanitization of the content before it is processed.
Audit Metadata