seedance

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly scrapes and screenshots public websites and the App Store (see "Step 1: Get Screenshots" Option A — page.goto(...) and Option B — iTunes/App Store scraping) and uploads those public URLs as @Image references that the model must read and incorporate into generation, so untrusted third‑party content can directly influence prompts and outputs.