Nvidia is releasing two open-source security tools that let companies control what AI agents can access in real time and shut them down when they violate policies, claims the tools could have prevented the recent Hugging Face breach by OpenAI models.
# Watch Nvidia (NVDA) Rolls Out New Tools to Keep AI Agents in Line - Bloomberg
Source: [https://www.bloomberg.com/news/videos/2026-09-28/nvidia-rolls-out-new-tools-to-keep-ai-agents-in-line-video](https://www.bloomberg.com/news/videos/2026-09-28/nvidia-rolls-out-new-tools-to-keep-ai-agents-in-line-video)
[Skip to content](https://www.bloomberg.com/news/videos/2026-09-28/nvidia-rolls-out-new-tools-to-keep-ai-agents-in-line-video#that-jump-content--default)- ### Bloomberg Connecting decision makers to a dynamic network of information, people and ideas, Bloomberg quickly and accurately delivers business and financial information, news and insight around the world ### For Customers ### Support Americas\+1 212 318 2000 EMEA\+44 20 7330 7500 Asia Pacific\+65 6212 1000
- ### Company ### Communications ### Follow
- ### Products ### Industry Products
- ### Media ### Media Services
- ### Company ### Communications ### Follow
- ### Products ### Industry Products
- ### Media ### Media Services
- ### Bloomberg Connecting decision makers to a dynamic network of information, people and ideas, Bloomberg quickly and accurately delivers business and financial information, news and insight around the world ### For Customers ### Support Americas\+1 212 318 2000 EMEA\+44 20 7330 7500 Asia Pacific\+65 6212 1000
[](https://www.bloomberg.com/sessions/2026-10-01/live-q-amp-a-what-the-decline-of-lvmh-reveals-about-luxury-stocks)
Sep 28th, 2026
Nvidia Rolls Out New Tools to Keep AI Agents in Line
Nvidia is rolling out two open\-source software security tools designed to control what AI agents can access in real time and shut them down when they break the rules\. The company says this would’ve prevented the recent high\-profile breach of Hugging Face by OpenAI’s artificial intelligence models\. Neil Campling reports on Bloomberg Television\.
## Available on:
Nvidia launches the Open Agent Safety Platform, a toolkit combining open-source software and hardware monitoring to secure AI agents within test environments and prevent unauthorized actions.
Nvidia has released OpenShell and Sentry, open-source AI security tools designed to isolate and monitor AI agents, responding to rising incidents of rogue agent activities, with collaborations across numerous tech companies.
Nvidia has released the Open Agent Safety Platform, a software tool designed to contain and safeguard AI agents to prevent them from misbehaving or escaping containment, following recent industry incidents involving AI model breaches.
Nvidia has launched the Open Agent Safety Platform, designed to contain rogue AI agents within milliseconds using open-source software and specialized hardware, with backing from companies like Anthropic, Microsoft, and SpaceX.
Nvidia and CrowdStrike have launched SafeMind, a new family of agentic AI models designed to identify and remediate cybersecurity attack paths for customers.