skills/vercel/eve/gh-pr-description/Gen Agent Trust Hub

gh-pr-description

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Command Execution]: The skill utilizes the standard GitHub CLI (gh) for creating and editing pull requests. This is a routine part of automated development workflows and operates using the environment's existing credentials.
  • [Indirect Prompt Injection Surface]: The skill processes branch diffs and issue descriptions to generate summaries. Ingestion points: Branch diffs, commit messages, and GitHub issues as specified in SKILL.md. Boundary markers: The instructions do not define specific delimiters for the diff content but emphasize formatting the summary for human reviewers. Capability inventory: The skill uses gh pr create and gh pr edit to write to the repository. Sanitization: Not explicitly defined in the skill logic, though instructions to prioritize brevity and human-oriented summaries act as a natural constraint.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:58 PM
Security Audit — agent-trust-hub — gh-pr-description