azure-ai-voicelive-py

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [Secure Authentication]: The skill promotes the use of DefaultAzureCredential and AzureKeyCredential managed via environment variables. This aligns with security best practices for avoiding hardcoded secrets.
  • [Network Communication]: The skill facilitates real-time bidirectional audio streaming via WebSockets. All communication targets official Azure Cognitive Services endpoints (e.g., *.api.cognitive.microsoft.com), which are well-known and trusted service domains.
  • [Dependency Management]: The skill utilizes standard, well-maintained libraries such as azure-ai-voicelive, aiohttp, and azure-identity. These are legitimate packages used for Azure service integration and asynchronous HTTP communication.
  • [Data Processing]: As a voice AI SDK, the skill is designed to ingest and process audio and text data. While this creates a surface for processing untrusted user input, the SDK provides the necessary framework for developers to implement their own application-level sanitization and safety logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 03:16 PM