Microsoft Agent Framework

The Microsoft Agent Framework is a development platform that enables organizations to build autonomous AI agents capable of completing complex tasks across enterprise systems and applications. This framework matters for AI governance because it provides structured controls for agent behavior, decision-making transparency, and integration with Microsoft's compliance and security infrastructure. Organizations deploying agent-based automation need clear oversight mechanisms to ensure agents operate within defined guardrails and maintain audit trails for regulatory requirements.

1 item

ResearchGlobal2026-08-06

11 Framework Flaws Put Every Agentic App Built on LangChain, AutoGen, and Google ADK at Risk

Check Point Research disclosed 11 vulnerabilities across five major AI agent frameworks, including LangChain, CrewAI, AutoGen, Microsoft Agent Framework, and Google ADK. The flaws include classic bug classes such as insecure deserialization and path traversal embedded in the infrastructure enterprises use to build agentic AI applications. A critical flaw in Microsoft Agent Framework enabled remote code execution triggered through prompt injection, while a Google ADK issue allowed unauthenticated code execution and credential theft on default cloud deployments.

agentic AI AI security prompt injection vulnerability disclosure LangChain Microsoft Agent Framework Google ADK supply chain security