Skills
skills/bonkey/skills/pr/Gen Agent Trust Hub

pr

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git and GitHub CLI (gh) commands to manage the PR lifecycle. This is the primary intended function of the skill and uses well-known development tools.
  • [DATA_EXFILTRATION]: The skill includes explicit instructions to avoid staging sensitive configuration files like .env or credential files when performing automatic commits.
  • [PROMPT_INJECTION]: The skill processes untrusted content from git history and existing pull request descriptions to generate new metadata. It mitigates risk by defaulting to opening the browser for PR creation, which ensures that the user reviews the generated title and body before submission.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 07:28 AM