design-tokens-transformer

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements logic for the automated transformation of design assets. It instructs the agent to read, parse, and generate code for file paths such as assets/round3/02-tokens.json, colors_and_type.css, and assets/round3/globals.css.
  • [EXTERNAL_DOWNLOADS]: The skill references external resources from well-known and trusted providers. It includes instructions to fetch font configurations from Google Fonts (fonts.googleapis.com) and references the official W3C Design Tokens Community Group schema (design-tokens.github.io).
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes external design token files (JSON/CSS) to generate production code.
  • Ingestion points: Files like 02-tokens.json and CSS handoff bundles.
  • Boundary markers: The instructions define strict schemas and 'FROZEN' rule annotations to delimit token data.
  • Capability inventory: The agent is tasked with file reading, value mapping, and stylesheet generation.
  • Sanitization: The skill includes normalization rules for hex codes, dimensions, and font stacks to ensure data consistency during the conversion process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — design-tokens-transformer