Google Agent Development Kit

Google Agent Development Kit is an open-source framework from Google for building AI agents, which are software systems that can plan tasks and call tools or other services with limited human direction. Because these agents can take actions inside a company's systems, such as reading data, triggering workflows, or making API calls, governance teams need to know how the kit handles permissions, logging, and human oversight. Enterprises adopting agent frameworks like this one should review whether built-in controls meet their internal policies and whether agent activity can be audited end to end.

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