azure-ai-document-intelligence-ts

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • [Unverifiable Dependencies] (LOW): The skill installs @azure-rest/ai-document-intelligence and @azure/identity. As these are official Microsoft packages (a trusted organization), the severity is downgraded from MEDIUM to LOW per the [TRUST-SCOPE-RULE].
  • [Indirect Prompt Injection] (LOW): The skill extracts text from external documents, which provides a surface for indirect prompt injection if the output is processed by an LLM without further sanitization.
  • Ingestion points: The skill ingests data via urlSource (URLs) and base64Source (local files) in multiple code examples.
  • Boundary markers: None are present in the provided snippets to delimit the extracted content from instructions.
  • Capability inventory: The skill possesses the capability to read local files (readFile) and perform network operations to Azure's REST API.
  • Sanitization: No explicit sanitization or content validation of the extracted document data is demonstrated in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 03:34 AM