pr-finalize
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [Command Execution]: The skill uses
gh(GitHub CLI) andgitcommands to access pull request data, such as titles, descriptions, and code diffs. These operations are read-only and limited to the context of PR analysis. - [Restricted Capabilities]: There are strong, explicitly stated rules that prevent the agent from using commands to approve pull requests, request changes, or post comments directly. This design pattern ensures that the agent's role is strictly analytical and that final actions require human intervention.
- [Data Processing Surface]: Because the skill is designed to analyze external data provided in pull requests, it inherently processes untrusted input from PR authors. The instructions mitigate potential issues by defining strict output formats and avoiding tools that would allow for the direct execution of commands based on ingested data.
Audit Metadata