pr-review
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from GitHub pull requests which could contain adversarial instructions.
- Ingestion points: Untrusted data enters the agent context via
gh pr viewandgh pr diff(SKILL.md). - Boundary markers: The skill does not define clear boundaries or provide instructions to ignore embedded commands within the PR description or code diffs.
- Capability inventory: The agent possesses the capability to perform write actions via
gh pr comment(SKILL.md). - Sanitization: No sanitization or filtering is applied to the content retrieved from the pull request before it is processed by the agent.
Audit Metadata