pr-review
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands including git and gh to manage repository state, create worktrees, and interact with the GitHub API.
- [REMOTE_CODE_EXECUTION]: The skill executes the project's own quality pipeline (e.g., composer fix, pest, tsc) to establish a green baseline for reviews. This involves executing code within the pull request but is a core functional requirement of the review process and is restricted to a temporary workspace.
- [PROMPT_INJECTION]: The skill ingests external content from pull request metadata and comments. It mitigates potential risks through strict sub-agent task scoping and requiring explicit user approval before performing any external write operations.
Audit Metadata