create-pr

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to perform repository operations including listing (gh pr list), editing (gh pr edit), and creating (gh pr create) pull requests.
  • [DYNAMIC_EXECUTION]: The skill executes a local Python script located at .github/scripts/validate_pr_body.py to validate generated pull request metadata before submission.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to generate PR content, creating a potential injection surface.
  • Ingestion points: Data is ingested from git branch names, commit messages, and issue descriptions (SKILL.md).
  • Boundary markers: The skill does not define specific prompt delimiters for external content but provides shell-level safety instructions.
  • Capability inventory: The skill has the ability to write to the repository's pull requests via the gh CLI and execute local scripts.
  • Sanitization: The instructions explicitly mandate passing generated values as separate quoted arguments and forbid the interpolation of untrusted text into shell syntax to prevent command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 01:12 AM