create-color

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests and interprets arbitrary Figma file content (see Step 4 "Gather Context" using figma_navigate / figma_get_file_data / figma_execute and the Step 4b extraction script) and then uses the extracted variant/style/token data to choose rendering strategies and drive subsequent figma_execute calls, so untrusted user-generated file content can materially influence agent actions.