pr-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI tool ('gh') to perform PR-related tasks. This involves executing commands such as 'gh pr view', 'gh pr diff', and 'gh api' to fetch data and submit reviews. These actions are limited to the intended scope of code review and use established tool patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill reads pull request content from GitHub, which acts as an ingestion point for untrusted data that could potentially contain malicious instructions.
- Ingestion points: Metadata and patch diffs are retrieved via 'gh pr view' and 'gh pr diff' (referenced in SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands within the diff content.
- Capability inventory: The skill possesses the capability to write to the repository by posting review comments and using the GitHub REST API via 'gh api'.
- Sanitization: There is no evidence of sanitization or escaping of the external PR data before it is processed by the agent.
Audit Metadata