跳到正文
Simon Willison's Weblog·· 5 天前精选AI 评分84

Simon Willison 推出编程智能体外部沙箱架构及三款服务端实现

External sandboxes for coding agents

AI 导读

Simon Willison 联合 AI 研究机构 Prime Radiant 发布了针对编程智能体的外部沙箱方案及三款服务端实现,让智能体执行的代码在独立沙箱中运行而智能体本身保留在沙箱外部。

推荐理由

该方案展示了智能体与代码执行环境物理分离的具体实现,读者可以借此解决本地模型代码执行时的注入攻击与安全隔离问题。

正文 · 原文

17th November 2026 - Link Blog

External sandboxes for coding agents. I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine.

I worked on this project with Prime Radiant, the AI research lab behind Superpowers and other projects.

My post on the Prime Radiant blog introduces the external sandbox pattern, where code executed by the agent runs inside a dedicated sandbox while the agent itself lives outside of that sandbox.

To demonstrate this pattern we've released three sandbox server implementations:

Each of these implementations offers the same localhost API. You can then configure Pi, Claude Code, or Codex to send API calls to that sandbox any time they want to execute code.

The sandboxes also include an optional HTTP/HTTPS allow-list proxy, so you can control exactly which hosts your agent's code is allowed to communicate with - plus a credential replacement mechanism to make authenticated API calls without sharing a secret with the agent. Here's the UI you can use to reconfigure that proxy while the sandbox is still running:

The network policy page with allowed destinations, the policy JSON editor and recent proxy activity

I continue to be fascinated by the challenge of safely running untrusted code. This external sandbox pattern provides a neat way to experiment with different approaches.

来源:Simon Willison's Weblog · simonwillison.net

EVAOO 主站实战落地 · AI Agent 与研发提效

看完情报?回到 EVAOO 主站直接上手工具与完整 SOP

返回 EVAOO 主站