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). The SKILL.md core workflows (e.g., "Analyze Invoice" and "Extract Layout" showing client.AnalyzeDocumentAsync with documentUri/invoiceUri and the "Build Custom Model" flow using a BlobContentSource with a blob-container SAS URL) explicitly instruct the agent to fetch and analyze arbitrary external document URLs/blob storage, which are untrusted third‑party content that can materially influence analysis and downstream decisions.