pollinations

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

• Third-party content exposure detected (high risk: 0.80). The skill accepts and processes arbitrary external URLs and user-provided media (e.g., scripts/image.sh --image-url and the "Vision support" / "Image Analysis" sections that include image_url in messages), so the agent will read/interpret untrusted third-party content supplied from the open web.