skills/vantanev/tstack/file-pr/Gen Agent Trust Hub

file-pr

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses GitHub CLI commands (gh pr create, gh api) to automate pull request creation and repository interaction.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external content (local code diffs) into pull request metadata, creating an indirect prompt injection surface.
  • Ingestion points: Local branch diffs and user prompts (SKILL.md).
  • Boundary markers: None specified for separating diff content from the PR description.
  • Capability inventory: Uses gh CLI to write data to remote repositories.
  • Sanitization: Instructs the agent to manually verify titles and descriptions for secrets before submission.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 08:46 AM