ai-multimodal

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly supports ingesting arbitrary public URLs and YouTube videos (see references/video-analysis.md and vision-understanding.md which show types.Part.from_uri usage for YouTube and public image URIs), so it will fetch and interpret untrusted, user-generated third‑party content as part of its analysis workflow, which can materially influence subsequent outputs and actions.