azure-ai-document-intelligence-dotnet

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

• Third-party content exposure detected (high risk: 1.00). The skill's core workflows (e.g., AnalyzeDocumentAsync and ClassifyDocumentAsync) explicitly ingest documents by URI (examples: "https://example.com/invoice.pdf", documentUri, receiptUri, and blob container SAS URLs) which means it reads and interprets arbitrary third-party web-hosted documents as part of its processing, exposing the agent to untrusted external content.