AutoGen

AutoGen is an open-source framework from Microsoft Research for building systems in which multiple AI agents, each powered by a language model, converse with one another and with tools to complete multi-step tasks. Because these agents can execute code, call external APIs, and take actions with limited human review, organizations deploying AutoGen-based applications need clear controls over what the agents are permitted to do. Governance teams should treat it as a source of autonomous-action risk, covering access permissions, audit logging, and the handling of sensitive data passed between agents.

1 item

ResearchGlobal2026-10-12

253 MCP Server Bugs and Six Framework Bypasses Expose Agent Authorization Gap

Researchers from Pennsylvania State University, Université Montpellier, and Dartmouth College demonstrated a simple prompt technique called Repeat-After-Me. It bypassed six major AI agent frameworks, including LangGraph, AutoGen, and Google's Agent Development Kit 2.0. A companion tool called ToFu identified 253 verified security flaws across 118 open-source Model Context Protocol (MCP) servers that enterprises may already be running. The core architectural problem is that agent frameworks treat the AI model's own output as sufficient authorization to execute actions, without an independent check before any action runs.

prompt injection agentic AI MCP servers LangGraph AutoGen Google Agent Development Kit agent authorization supply chain risk