pollinations

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to include and analyze external content (e.g., "Vision support: Include image_url" and the image/image-to-image and audio transcription sections that accept arbitrary image URLs or uploaded audio/files), meaning untrusted public content is ingested and used to drive analyses and responses, which could enable indirect prompt injection.