figma-to-code

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests third‑party Figma content — SKILL.md and references/figma-export-guide.md instruct fetching Figma JSON via the Figma REST API (curl with FIGMA_TOKEN) and using user-provided screenshots/images read by the Read tool, and parse_figma_json.js plus the workflow show that this untrusted, user-generated content is parsed and directly drives code-generation decisions.