azure-ai-formrecognizer-java

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the com.azure:azure-ai-formrecognizer dependency from Microsoft, which is a trusted organization. This library is used for official integration with Azure AI Document Intelligence services.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting data from untrusted external sources.
  • Ingestion points: Untrusted data enters the agent context via documentUrl in beginAnalyzeDocumentFromUrl and blobContainerUrl in beginBuildDocumentModel (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are used to prevent the agent from executing commands embedded within the documents being analyzed.
  • Capability inventory: The skill is capable of reading local files using BinaryData.fromFile and making network requests to Azure's Document Intelligence API endpoints.
  • Sanitization: There is no evidence of URL validation, schema enforcement for the documents, or sanitization of the OCR output before it is returned to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 10:55 AM