agent-framework-azure-ai-py

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Command and Dynamic Execution]: The skill provides developer patterns for executing Python code using both a cloud-hosted interpreter and local scripts via a subprocess runner. These are intended for data analysis, mathematical calculations, and modular agent capabilities.
  • [Indirect Prompt Injection Surface]: The framework is designed to ingest and process data from untrusted sources, including user queries, web search results, and external Model Context Protocol (MCP) servers. The documentation proactively addresses this risk by providing tools for adversarial scanning and quality evaluation.
  • [External Dependencies]: The instructions recommend installing the official Microsoft Agent Framework packages and related evaluation tools from the public Python Package Index (PyPI).
  • [Security Best Practices]: The skill emphasizes secure authentication patterns, explicitly recommending DefaultAzureCredential over hardcoded keys and demonstrating the use of context managers to ensure secure handling of network transports and credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 02:17 PM
Security Audit — agent-trust-hub — agent-framework-azure-ai-py