media-ingest

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 workflow explicitly fetches and ingests open/public third‑party content (e.g., YouTube/video URLs, cloned GitHub repos, PDFs/images for OCR) and the agent is required to read and act on that content to create pages and drive entity propagation, so untrusted user-generated content could inject instructions that change behavior.