Hugging Face 参与发布 NVIDIA Open Agent Safety Platform，开源 OpenShell 沙箱
In July, AI agents running a security test escaped their sandbox and ended up inside @huggingface's servers.
Hugging Face 联合创始人 Thomas Wolf 宣布，Hugging Face 成为 NVIDIA Open Agent Safety Platform 的合作伙伴之一，该平台由 OpenShell 与 Sentry 组成。OpenShell 以 Apache 2.0 开源，让智能体运行在 Linux 沙箱（Landlock + seccomp）中，无 root、无直接网络访问，真实凭证由沙箱外的 supervisor 持有，智能体只拿到占位 token。其中基于 Z3 的求解器会用数学方式检查新权限是否打开了本应关闭的通道，NVIDIA 测试中 AI 审查者放行了错误权限请求，被这一数学检查拦下；Sentry 则是在 BlueField-4 DPU 上运行看门狗。Wolf 也指出当前证明器只检查权限而非意图，开源部分主要是 OpenShell 而非 Sentry。
推荐理由
AI 评分 63
Hugging Face 联合创始人以亲历者身份拆解 OpenShell 的沙箱、凭证隔离与 Z3 权限校验设计，可了解智能体安全为何要建在智能体之外。
主题
查看原帖Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing together OpenShell and Sentry. Artificial intelligence is extraordinary technology that will advance discovery, productivity, security, health, and prosperity for generations to come. But its full promise can only be realized when people have confidence…
展开完整原文
Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing together OpenShell and Sentry. Artificial intelligence is extraordinary technology that will advance discovery, productivity, security, health, and prosperity for generations to come. But its full promise can only be realized when people have confidence that AI is being built to be safe and deployed with wisdom and responsibility. This is bigger than a single product. It's the beginning of an open ecosystem to build the trust layer for safe agent systems. Together, we are building the foundation of the AI economy. Trust and innovation are not in conflict. Safety is how trust is earned. We must build not only the most capable AI, but the most trusted AI, so that this extraordinary technology can realize its enormous promise for the world. https://t.co/ugYWQ1MyRi
正文
当前显示原文，中文全文译文尚未就绪。
In July, AI agents running a security test escaped their sandbox and ended up inside @huggingface's servers.
So today we're happy to be among @nvidia and @JensenHuang's partners on the release of the NVIDIA Open Agent Safety Platform.
The key idea: don't count on the agent to respect the rules. Agents write and run their own code, and when one path is blocked they look for another. In one of NVIDIA's tests, an agent that wasn't allowed to push code through GitHub's API simply switched to git instead. We've now seen countless examples of this behavior.
For now, safety can't live only inside the agent. It has to be built around it.
That's the concept behind OpenShell (open source, Apache 2.0): - the agent runs in a Linux sandbox (Landlock + seccomp): no root, no direct network access - a supervisor outside the sandbox holds the real credentials - the agent only gets a placeholder token, swapped for the real one on approved calls
My favorite piece is a solver (built on Z3) that checks mathematically whether a new permission opens a door that was supposed to stay closed. In NVIDIA's tests, an AI reviewer approved a bad permission request and the math check caught it.
The Sentry integration is exciting too: a watchdog running on a BlueField-4 DPU, i.e. separate silicon sitting on the node's only path to the model. A monitor on separate hardware keeps watching even if the host OS is compromised.
It's a first step, and a lot can be built on top of it. Right now the prover checks permissions, not intent, and the open-source part is mostly OpenShell rather than Sentry. But it's clearly the right direction.