figma-design-extraction

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses content from third-party Figma files (figma.com) using get_metadata, get_variable_defs, get_design_context, and get_screenshot, and it treats that untrusted, user-provided content as authoritative input that directly affects extraction, token merging, and downstream actions.