design-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a deterministic audit process for UI implementations. It uses local scripts to perform file system analysis without network access.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes @google/design.md for linting tasks. As this originates from a trusted organization, it is considered safe and standard for the described workflow.
  • [COMMAND_EXECUTION]: The skill defines local audit scripts (check-classes.ts, check-tokens.ts) which are executed via Bun. These scripts perform deterministic text and CSS parsing on local project files to ensure parity with design tokens. No evidence of unauthorized command execution or argument injection was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:06 PM
Security Audit — agent-trust-hub — design-workflow