code-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its core functionality.
- Ingestion points: The agent reads and analyzes untrusted source code provided in pull requests or files (SKILL.md).
- Boundary markers: There are no specified delimiters or instructions to ignore embedded commands to mitigate the risk of instructions hidden in code comments or logic.
- Capability inventory: The skill is capable of performing 'fix, test, [and] commit' operations, implying filesystem write and command execution permissions for the testing phase (SKILL.md).
- Sanitization: No input validation or sanitization is present to filter malicious instructions from the code being reviewed.
Audit Metadata