Microsoft has released the Agent Governance Toolkit, an open-source runtime security layer for AI agents that maps directly to OWASP's top 10 agentic AI risks. The toolkit addresses threats like prompt injection, goal hijacking, tool misuse, rogue agents, and identity abuse. It comprises seven modular components — including Agent OS, Agent Mesh, Agent Runtime, Agent SRE, Agent Compliance, and Agent Lightning — available in Python, TypeScript, Rust, Go, and .NET. Designed to be framework-agnostic, it integrates with LangChain, CrewAI, Google ADK, and Microsoft Agent Framework without requiring code rewrites. Currently in public preview under an MIT license, Microsoft plans to transition it to a foundation-led governance model in collaboration with the OWASP agentic AI community.
Sort: