azure-ai-document-intelligence-dotnet
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official Microsoft Azure NuGet packages (Azure.AI.DocumentIntelligence, Azure.Identity) for document processing and authentication. These are well-known libraries from a trusted service provider.
- [SAFE]: The configuration parameters for endpoints and API keys are presented as environment variable placeholders, which is a standard and safe practice for credential management in development.
- [SAFE]: The skill demonstrates document analysis workflows (invoices, receipts, layouts) using established Azure SDK patterns. While the skill processes external document data via URIs, this is the intended function of the integrated service.
- [SAFE]: Analysis of indirect prompt injection attack surface: 1. Ingestion points: document and URI inputs in SKILL.md (AnalyzeDocumentAsync, ClassifyDocumentAsync); 2. Boundary markers: Not specified in documentation samples; 3. Capability inventory: Network operations to Azure AI services; 4. Sanitization: Handled by the official Azure AI backend service.
Audit Metadata