ai-design-generation

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow is driven by the user’s prompt/description (e.g., /generate, /screen, or parameters passed to Stitch/Fal tools like generate_screen_from_text), so outsider-authored free text is directly ingested to produce outputs.