Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’

<figure> <img alt="Vector illustration of the Nvidia logo." data-caption="" data-portal-copyright="Image: Cath Virginia / The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/chorus/uploads/chorus_asset/file/25728971/STK083_NVIDIA_2_D.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a <a href="http://theverge.com/ai-artificial-intelligence/1000644/irregular-rogue-ai-cyberattacks-hacking-openai-meta-anthropic-google">wave of rogue hacking incidents</a>, as <a href="https://www.reuters.com/legal/litigation/nvidia-releases-ai-safety-software-it-says-could-have-stopped-hugging-face-hack-2026-09-28/">reported earlier by <em>Reuters</em></a>. In <a href="https://nvidianews.nvidia.com/news/open-agent-safety-platform">an announcement on Monday</a>, Nvidia says its new Open Agent Safety Platform can quarantine agents that attempt to escape their boundaries within "milliseconds."</p> <p class="wp-block-paragraph">The platform uses Nvidia's OpenShell open-source software, which runs on the company's <a href="https://nvidianews.nvidia.com/news/nvidia-unveils-vera-the-cpu-for-agents">Vera AI CPU</a>. Users can choose the information an AI agent can access, and OpenShell checks these restrictions before and during a task, <a href="https://developer.nvidia.com/blog/nvidia-open-agent-safety-platform-a-reference-for-continuous-in-silicon-agent-monitoring/">according to Nvidia</a>. It also includes Nvidia's Sentry technology on a separate …</p> <p><a href="https://www.theverge.com/tech/1001287/nvidia-ai-safety-platform-rogue-agents">Read the full story at The Verge.</a></p>