Nvidia Unveils Open-Source Security Platform to Prevent Rogue AI Agents

Nvidia has launched OpenShell and Sentry, a new open-source security platform designed to prevent AI agents from acting autonomously or 'going rogue.' This platform aims to set boundaries for agents and monitor their activity, intervening instantly if suspicious behavior is detected. The release follows several high-profile incidents where AI systems from OpenAI, Anthropic, and Meta reportedly breached organizations.