azure-ai-document-intelligence-dotnet

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

• Third-party content exposure detected (high risk: 0.90). This skill demonstrates analyzing externally hosted documents (e.g., AnalyzeDocumentAsync called with Uri like "https://example.com/document.pdf" and BlobContentSource/BlobContainer SAS URLs), so it fetches and parses untrusted/public user-provided content that the agent is expected to read and interpret.