content-review

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

• Third-party content exposure detected (medium risk: 0.30). In the content-review workflow, the required runtime path extracts and reads arbitrary UI text from a selected Figma design via python3 .../figma_text.py extract <ch> <nodeId> (which calls scan_text_nodes and outputs each text node’s characters), so outsider-authored text embedded in Figma can be ingested at runtime.