azure-ai-projects-py

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • Standard Environment Variable Architecture: The skill relies on standard configuration techniques using environment variables like AZURE_AI_PROJECT_ENDPOINT and AZURE_AI_MODEL_DEPLOYMENT_NAME. These are populated dynamically at runtime rather than hardcoding credentials inside the skill package.
  • Least-Privilege Token Authentication Guidelines: The documentation promotes the use of DefaultAzureCredential from azure.identity, which integrates with Azure CLI, VS Code developer configurations, and Managed Identities without code changes. This is aligned with security best practices to eliminate hardcoded secrets.
  • Controlled Sandbox Tool Configuration: References to runtime utilities like CodeInterpreterTool and FileSearchTool demonstrate how to attach cloud-hosted sandboxed environments and search capabilities to an agent via standard SDK parameters, avoiding standard privilege or execution concerns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:18 PM
Security Audit — agent-trust-hub — azure-ai-projects-py