pr-review

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a PR review workflow using standard GitHub CLI (gh) and Git commands. It gathers context from the PR and performs analysis based on correctness, security, and efficiency.
  • [SAFE]: Instructions explicitly forbid the agent from performing network-based mutations (e.g., posting reviews) and instead mandate emitting a local JSON payload for validation.
  • [SAFE]: Data processing involves reading repo files and PR diffs, which is expected for a review tool. It uses a standalone Python script with standard jsonschema validation to ensure the output matches a strict, locally provided schema.
  • [SAFE]: The skill follows least-privilege principles by scoping its actions to local file writes and context gathering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 08:50 AM
Security Audit — agent-trust-hub — pr-review