design-tokens-tailwind

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script (scripts/generate-tailwind-theme.mjs) to automate the conversion of design tokens. This execution is performed within the local project environment using code included in the skill package.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific JSON data, which represents a standard data ingestion surface.
  • Ingestion points: Data is read from design-tokens.json or user-defined JSON files.
  • Boundary markers: The instructions direct the agent to inspect file contents, which is necessary for its function.
  • Capability inventory: The skill allows for local file writes and execution of the bundled conversion script.
  • Sanitization: The conversion script implements strict character filtering for token names and formats values for CSS, providing protection against code injection in the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 10:05 AM
Security Audit — agent-trust-hub — design-tokens-tailwind