requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The subagent defined in
code-reviewer.mdis vulnerable to instructions embedded within the code changes it reviews. An attacker could include comments or strings in the source code designed to manipulate the agent's review results. - Ingestion points: Code changes retrieved via
git diffincode-reviewer.md. - Boundary markers: Absent. There are no delimiters or specific instructions to the agent to disregard instructions contained within the code content itself.
- Capability inventory: The agent performs analysis and provides a merge readiness assessment, which influences the development pipeline.
- Sanitization: Absent. The code content is processed as raw text without validation or escaping.
Audit Metadata