review-pr
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection Surface: The skill retrieves content from Pull Request titles, bodies, and diffs, which is then analyzed by the agent. This content represents an ingestion point for untrusted data. Ingestion points: gh pr view and gh pr diff commands in SKILL.md. Boundary markers: The skill does not define specific delimiters to isolate PR content during analysis. Capability inventory: The agent has the capability to execute bash commands and post comments to GitHub. Sanitization: No explicit sanitization of PR content is described.
- Command Execution Surface: The skill incorporates user-provided arguments directly into shell commands, such as gh pr view $ARGUMENTS. While standard for CLI-based automation tools, this pattern relies on the underlying platform to ensure input is handled safely.
Audit Metadata