code-review
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill acts on external, untrusted data by reviewing code from pull requests and local changes, creating an indirect prompt injection surface where malicious instructions could be embedded in code comments.
- Ingestion points: PR content, feature branch changes, and local code.
- Boundary markers: Not specified.
- Capability inventory: Mentions invocation of the 'glossary' skill tool.
- Sanitization: Not specified.
- [NO_CODE]: The skill consists purely of natural language instructions and does not include any executable scripts, dependencies, or configuration files.
Audit Metadata