review-github-pr
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
ghCLI to interact with GitHub repositories. It constructs commands using variables (like repository owner, name, and file paths) extracted from the PR metadata. This is standard functionality for GitHub integration and is handled appropriately. - [PROMPT_INJECTION]: As the skill reads and analyzes untrusted code from pull requests, it is theoretically susceptible to indirect prompt injection (where malicious instructions are hidden in the code being reviewed). This risk is mitigated by the skill's specific task instructions and the requirement for the user to review and manually approve the generated comments before they are posted to GitHub.
- [DATA_EXFILTRATION]: The skill requires internet access to communicate with GitHub's API via the
ghtool. No evidence was found of data being sent to unauthorized third-party services or non-whitelisted domains.
Audit Metadata