azure-ai-formrecognizer-java

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate documentation and code samples for an official cloud service SDK. No malicious patterns such as obfuscation, credential theft, or unauthorized data access were found.
  • [EXTERNAL_DOWNLOADS]: References the official Microsoft Azure Document Intelligence SDK for Java (com.azure:azure-ai-formrecognizer).
  • [COMMAND_EXECUTION]: Code examples demonstrate reading local files (e.g., document.pdf) for the purpose of document analysis.
  • [PROMPT_INJECTION]: As a tool designed to extract text from external documents (PDFs, images, URLs), it presents an indirect prompt injection surface where malicious text in a scanned document could influence the behavior of an agent processing the results. Ingestion points: SKILL.md (document analysis methods); Boundary markers: Absent; Capability inventory: File system read and network transmission via Azure SDK; Sanitization: No explicit content filtering is shown in the SDK usage examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 11:59 AM