github-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub pull requests, including titles, bodies, and code diffs. This creates a surface where malicious instructions embedded in a PR could attempt to influence the agent's review logic or actions.
- [COMMAND_EXECUTION]: Uses system commands such as
git,gh, andcurlto manage local repositories and interact with the GitHub API. - [EXTERNAL_DOWNLOADS]: Fetches pull request data from the official GitHub API (
api.github.com). This is a well-known service and is considered safe for the skill's intended purpose per trust scope rules. - [DYNAMIC_EXECUTION]: Employs
python3 -cto parse JSON responses from API calls. The Python code is hardcoded within the skill and uses standard libraries to handle data safely, posing minimal risk.
Audit Metadata