fix-coderabbit-review
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from external GitHub PR review comments. While this is an indirect prompt injection surface, the instructions include specific mitigations, telling the agent to 'evaluate each review item technically before changing code' and 'do not apply suggestions blindly'.
- [COMMAND_EXECUTION]: The workflow involves executing local scripts (
pr-review.ts,resolve_pr_issues.sh) and standard project commands (pnpm run lint,pnpm run test). These actions are consistent with the skill's purpose of code remediation and verification. - [EXTERNAL_DOWNLOADS]: The scripts communicate with GitHub's REST and GraphQL APIs using a user-provided
GITHUB_TOKEN. These network operations are directed at a trusted service and are essential for exporting and resolving PR issues.
Audit Metadata