canvas-design-codex

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were identified. The skill's instructions are focused on verifying visual outputs such as Canvas, SVG, and WebGL through automated screenshot and pixel analysis.
  • [COMMAND_EXECUTION]: The skill invokes helper scripts located in the .shared\visual-runtime directory for its operational workflow. These tools—capture_page.mjs, image_bounds.py, make_contact_sheet.py, and visual_lint.mjs—are internal platform utilities used to perform visual verification and do not represent a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 08:02 AM
Security Audit — agent-trust-hub — canvas-design-codex