design-code
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several local validation scripts using Python and Node.js, including
lint_hardcodes.py,validate_theme_refs.py,contrast.py,taste_audit.mjs,verify_states.mjs, andaccuracy_report.mjs. These are part of the project's internal toolkit for maintaining code quality. - [SAFE]: The skill operates entirely within the local file system, reading design tokens, framework adapters, and accessibility guidelines. It uses standard shell commands to check for the presence of the required 'kit' directories before proceeding, ensuring a predictable execution environment.
Audit Metadata