code-review
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from the repository being reviewed.\n
- Ingestion points: Pull request diffs, historical PR comments, and project-specific CLAUDE.md files are read into the agent context in SKILL.md (Steps 2, 3, and 4).\n
- Boundary markers: The instructions do not define delimiters or specific directives to the agents to disregard potentially malicious instructions embedded within the files or comments it reviews.\n
- Capability inventory: The skill possesses the gh pr comment capability to post content back to GitHub.\n
- Sanitization: No sanitization or validation of the data retrieved from the repository is performed before it is processed by the AI agents or included in the review output.
Audit Metadata