review-pr

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local scripts (scripts/pr, scripts/pr-review) and system commands (git, gh, rg). These are used to manage PR worktrees, fetch diffs, and perform search operations within the codebase.
  • [PROMPT_INJECTION]:
  • Ingestion points: Processes untrusted external content from Pull Request descriptions and diffs via gh pr diff and git log.
  • Boundary markers: The skill uses structured JSON and Markdown templates for review findings, providing a clear schema for the agent's output.
  • Capability inventory: The skill allows editing PR metadata (assigning reviewers) and executing tests via a local wrapper script. All activities are scoped to specific worktree directories.
  • Sanitization: The instructions mandate a read-only execution contract and artifact validation steps to ensure that the analysis remains within its intended scope.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — review-pr