design-qa
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several local Python and Node.js scripts (
scripts/validate_tokens.py,scripts/validate_contrast.py,scripts/lint_hardcodes.py,scripts/measure_render.mjs). These scripts are intended for automated linting and rendering tasks within the project repository. - [INDIRECT_PROMPT_INJECTION]: The skill involves processing external data such as
workflows/design-qa.mdand user-specified source or HTML files. - Ingestion points: Files located at
workflows/design-qa.md,<src>, and<file.html>are read or processed. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The agent utilizes
python3andnodeto run local scripts against these files. - Sanitization: Not explicitly mentioned, though the scope is restricted to design linting and headless rendering.
Audit Metadata