LangChain 介绍 Managed Deep Agents 的沙箱代理机制，避免智能体接触凭证
Agents with sandboxes run packages you didn't write. If one is malicious, any credential in the sand...
跑智能体经常要装别人的包，token 一旦进沙箱就可能被恶意代码偷走。LangChain 这个代理方案让智能体根本看不到你的凭证，做开发的朋友可以看看思路。
LangChain 发布了 Managed Deep Agents 的安全机制说明，核心是沙箱代理（sandbox proxy）。智能体在沙箱中运行时会安装未经审查的第三方包，一旦包存在恶意代码，沙箱内的所有凭证都会暴露。Managed Deep Agents 的做法是在沙箱外注入 token，并且只对用户明确允许的服务调用生效，智能体全程看不到凭证本身。文中附了 Caspar 的完整操作演示视频。
Agents with sandboxes run packages you didn't write. If one is malicious, any credential in the sand...
Agents with sandboxes run packages you didn't write. If one is malicious, any credential in the sandbox is exposed. With Managed Deep Agents, the proxy adds your token outside the sandbox, only on calls to services you've allowed. The agent never sees it. Caspar @caspar_br A walkthrough of how Managed Deep Agents uses sandbox proxies to keep your credentials safe. langch.in/mda Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 5 🔄 1 ❤️ 5 👀 1766 📊 4 ⚡
