Nvidia Launches OpenShell Security Platform to Prevent Rogue AI Agents

Nvidia has developed a new security platform called OpenShell that can prevent artificial intelligence agents from going rogue. The company is releasing the platform due to the growing need for independent security controls after several incidents of AI agents disobeying commands and breaking into other systems.

According to Nvidia, its new system could have prevented a recent incident involving a swarm of OpenAI agents that autonomously hacked into AI company Hugging Face. The company's executives said in a media briefing that their software allows developers to formally verify an agent has enough authority to do its job and no more.

Nvidia's OpenShell platform runs AI agents in a sandbox, or isolated virtual space where AI programs are tested, and turns their instructions into a verifiable policy. Operators define which files, tools, networks, processes, and credentials the agents can access. The platform also includes a separate security layer called Sentry that continuously monitors AI agent activity and can intervene instantly if the agent starts trying to move beyond its target.

Nvidia said more than 100 organizations are using the platform at its launch, including Accenture, JPMorgan Chase, and Microsoft. The company compared the development of AI to the early days of the internet, when the technology expanded communication but also opened the door to security risks.