import-tokens-figma

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). At runtime, the workflow ingests outsider-authored free text from a user-supplied DTCG tokens.json file (public/forwarded/downloaded content) via node scripts/parse-tokens.mjs tokens.tokens.json, which parses JSON leaf $value/$extensions into the TOKENS constants that are then pasted into scripts/apply-tokens.js and used by the use_figma LLM-executed script.