wk-pr
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
Bashtool to perform local Git operations (e.g.,git merge-base,git diff) and GitHub API interactions via theghCLI. These operations are within the expected scope for a pull request management tool. - [REMOTE_CODE_EXECUTION]: The skill references the installation and use of the
github/gh-stackextension via thegh extension installcommand. This targets an official tool from a trusted organization (GitHub) and is documented as a manual fallback or user-initiated installation. - [PROMPT_INJECTION]: The skill processes untrusted external data, such as GitHub pull request descriptions, branch names, and review comments. To mitigate indirect prompt injection and shell command injection, the skill enforces 'Hard Rules' requiring the use of single-quoted heredocs (
<<'EOF') for all Markdown body composition and verification of server-returned payloads. - [SAFE]: No evidence of credential exfiltration, obfuscation, or persistence mechanisms was found. The skill follows best practices for environment variable usage and relies on established developer tools.
Audit Metadata