github-review
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from the Pull Request data it processes.
- Ingestion points: Reads pr.diff, files.json, and comments.json which contain untrusted content.
- Boundary markers: There are no documented delimiters to separate the untrusted PR content from the AI's system instructions.
- Capability inventory: The skill can publish reviews and inline comments to GitHub repositories.
- Sanitization: The skill does not perform sanitization of the PR data before analysis.
Audit Metadata