resolve-pr-feedback
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses
gitandgh(GitHub CLI) to perform repository operations including committing changes and interacting with the GitHub GraphQL API. - [PROMPT_INJECTION]: Vulnerable to indirect prompt injection because it ingests untrusted data from pull request comments which could contain malicious instructions.
- Ingestion points: Untrusted data enters the context via
scripts/get-pr-commentswhich fetches review threads, comments, and review bodies. - Boundary markers: The instructions do not define clear boundaries or 'ignore' instructions to prevent the model from following commands embedded in the comments.
- Capability inventory: The skill has the capability to write to the local filesystem, commit code, and execute API mutations (resolving threads, posting replies).
- Sanitization: There is no evidence of sanitization, filtering, or escaping performed on the PR comment text before it is processed by the agent.
Audit Metadata