skills/yulonghe97/ystack/pr/Gen Agent Trust Hub

pr

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill runs shell commands for Git and GitHub operations (git push, gh pr create) and executes package manager scripts (pnpm fix, pnpm typecheck). These actions are appropriate for its function of automating pull requests.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads local plan and decision files to generate pull request metadata. Ingestion points: .context/*/PLAN.md, DECISIONS.md. Boundary markers: No explicit delimiters are used. Capability inventory: Remote branch pushing and PR creation. Sanitization: No explicit validation of file content is performed. The risk is low given the data originates from the local development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 07:52 AM
Security Audit — agent-trust-hub — pr