code-review
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill uses terms like 'ignore' and 'override' within the functional context of managing code review feedback (e.g., ignoring optional nits or resolving disputes), which does not constitute a malicious attempt to bypass safety guardrails.
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to analyze external, untrusted source code provided in pull requests or feature implementations.
- Ingestion points: Code provided for review as described in the 'When to Use' section of SKILL.md.
- Boundary markers: No specific technical delimiters are defined to isolate the content of the code under review from the agent's core instructions.
- Capability inventory: The skill is purely instructional and does not itself define or use execution tools or network access.
- Sanitization: The instructions emphasize identifying a lack of sanitization in the reviewed code but do not provide sanitization mechanisms for the data ingestion process itself.
- [NO_CODE]: The skill consists of Markdown instructions and a YAML configuration file. No executable scripts, binaries, or other code files are provided.
Audit Metadata