visual-verify

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Command Execution]: The skill invokes local Node.js scripts located in /workspace/tools/ and /workspace/skills/. These scripts, such as review-thumb.mjs and img.mjs, are used to process images, create tiled sheets, and generate zoomed crops for manual inspection.
  • [File System Interaction]: The instructions describe workflows that read image files from attachments/ and project-specific renders/ directories, and save processed review images to a review/ folder. This local file access is standard for tools designed to audit rendering outputs within a development workspace.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 05:18 AM