doc-analyzer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests "fetched documentation" (doc-fetcher → doc-analyzer) and processes content and source_url fields from external/public documentation (e.g., https://fastapi.tiangolo.com/... and other fetched docs), so it reads and interprets open third‑party web content as part of its workflow.