Skills
skills/microsoft/skills/azure-ai-voicelive-py/Gen Agent Trust Hub

azure-ai-voicelive-py

Pass

Audited by Gen Agent Trust Hub on Feb 14, 2026

Risk Level: LOWEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill requires the installation of azure-ai-voicelive, aiohttp, and azure-identity.\n
  • Evidence: SKILL.md Installation section.\n
  • Context: These are official packages from the azure organization, which is a trusted source per [TRUST-SCOPE-RULE].\n- [DATA_EXFILTRATION] (LOW): The skill facilitates network communication with Azure Cognitive Services endpoints.\n
  • Evidence: SKILL.md Quick Start and Authentication sections.\n
  • Context: The communication is directed to *.api.cognitive.microsoft.com, which is a trusted domain for this service. No unauthorized exfiltration was detected.\n- [CREDENTIALS_UNSAFE] (INFO): Documentation includes examples of API key authentication using AZURE_COGNITIVE_SERVICES_KEY.\n
  • Evidence: SKILL.md and references/acceptance-criteria.md.\n
  • Context: The skill correctly identifies hardcoded keys as an anti-pattern and recommends DefaultAzureCredential for production environments.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 14, 2026, 04:59 PM