pr-creator

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill runs npm run preflight to perform a local build and lint check prior to PR creation.
  • [COMMAND_EXECUTION]: It uses the GitHub CLI (gh pr create) to automate the submission of pull requests to GitHub.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from repository PR templates which could be used as an indirect prompt injection surface.
  • Ingestion points: File reads from .github/pull_request_template.md and other template variants.
  • Boundary markers: Not present.
  • Capability inventory: Subprocess execution via npm and gh CLIs.
  • Sanitization: Not present; the template content is used directly to structure the PR description.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 04:52 PM
Security Audit — agent-trust-hub — pr-creator