reviewing-code
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and configuration are purely instructional and do not include any executable scripts, binaries, or requests for sensitive permissions.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its core function of analyzing external code and pull request data. Evidence: 1. Ingestion points: requested changes, repository/PR context, and code diffs (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are provided to ignore commands embedded in the processed code. 3. Capability inventory: No tool execution, subprocess calls, or file-write capabilities are defined within the skill. 4. Sanitization: No validation or escaping of the ingested code content is performed. This vulnerability is inherent to the primary purpose of code review.
Audit Metadata