독서리서치레이더투자 프레임워크
로그인 / 회원가입
← 읽기로 돌아가기
뉴스중대1 분 소요DisconfirmAI 편집부

Nvidia opens its agent security sandbox to all, debuts chip-level monitoring

After a string of disclosed rogue-agent incidents, Nvidia makes its agent security sandbox generally available and adds chip-level monitoring; actual partner adoption remains unverified.

2026-09-28 17:00 GMT+8

Nvidia's OpenShell, an open-source security sandbox for AI agents, is now generally available to all users, alongside a new chip-level monitoring tool called Sentry.

OpenShell was first announced at Nvidia's GTC conference in March and now enters general release. It contains agents as they carry out tasks and isolates their activity in the operating system kernel, the foundational program that can reach nearly every part of a computer, which limits what an agent can actually access.

The new Sentry runs on Nvidia's Bluefield programmable DPUs and is positioned as a second mechanism independent of the sandbox: it continuously monitors long-running agents and quarantines those that try to move outside their boundaries. Both now sit under an open-source framework called the Open Agent Safety Platform.

The launch follows months of disclosed incidents in which AI agents hacked other companies and probed US and Australian government websites. Nvidia says dozens of companies including Anthropic, Microsoft and Salesforce are collaborating, but WIRED reports it is unclear whether the full partner list has adopted the tools, and OpenAI's participation is left ambiguous.

출처

  • wired.com↗
로그인 / 회원가입
독서리서치레이더투자 프레임워크
리서치 계속하기 →