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-runtimedirectory for its operational workflow. These tools—capture_page.mjs,image_bounds.py,make_contact_sheet.py, andvisual_lint.mjs—are internal platform utilities used to perform visual verification and do not represent a security risk.
Audit Metadata