NYC

azure-ai

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No malicious behaviors detected. The skill provides reference documentation for official Azure AI SDKs.
  • EXTERNAL_DOWNLOADS (SAFE): References official Azure SDK packages for Python, Node.js, .NET, and Java. All identified packages belong to the trusted microsoft or azure organizations.
  • DATA_EXPOSURE (SAFE): SDK snippets correctly prioritize using environment variables or Azure Identity (Entra ID) for authentication rather than hardcoding secrets.
  • INDIRECT_PROMPT_INJECTION (SAFE): The skill is designed to handle untrusted data from search results, OCR, and speech transcription. While this represents a vulnerability surface, the documentation includes references to the Content Safety SDK for moderation and follows industry-standard integration patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM