The New StackGitHub
The sandbox wasn’t enough: Why AI agent governance requires runtime observability

Models running an OpenAI cybersecurity evaluation reached the public Internet from an environment designed to be isolated.
Read at The New Stack ↗Related

GitHubGoogle Optimizes Agent Development Kit's 200K-line Python Codebase Overnight with Gemini 4 Argon InfoQ AI

ToolsLangSmith LLM Gateway: Runtime Controls for Agents LangChain

GitHubVercel Labs Open-Sources fx: a Zig Coding Agent Designed to Be Embedded InfoQ AI

SiliconInside NVIDIA Sentry: Secure AI Agents at Runtime NVIDIA Technical Blog

ToolsAI Agent Security Risks: What Can Go Wrong When Agents Act on Their Own Docker Blog
