agent-framework-azure-ai-py

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate documentation and code samples for the Microsoft Agent Framework (Azure AI Agents). No malicious patterns, obfuscation, or unauthorized data access attempts were detected.
  • [CREDENTIALS_UNSAFE]: The skill demonstrates secure authentication practices by using azure.identity.aio credentials (DefaultAzureCredential, AzureCliCredential) and environment variables for configuration. No hardcoded API keys or secrets are present.
  • [EXTERNAL_DOWNLOADS]: The skill references official Python packages (agent-framework, agent-framework-azure-ai) and uses a Model Context Protocol (MCP) endpoint from a well-known, trusted domain (learn.microsoft.com).
  • [PROMPT_INJECTION]: Instructions provided to the agents are standard functional descriptors (e.g., "You are a helpful assistant") and do not contain bypass markers or attempts to override system safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:36 AM