帖子详情

LangChain@LangChainAI

发布时间（北京时间）
2026-10-17 01:27

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 🔗 View on Twitter 🔗 View Quoted Tweet

媒体保存失败：[Errno 104] Connection reset by peer

▶ 打开视频地址

帖子 ID: 2111146976683425860
Markdown: /app/data/archive/2026/10/16/LangChainAI/2111146976683425860/post.md
保存状态: complete

查看 Markdown 内容

---
tweet_id: "2111146976683425860"
author: "LangChainAI"
published_at: "2026-10-16T17:27:17+00:00"
source_url: "https://x.com/LangChain/status/2111146976683425860"
---

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](https://pbs.twimg.com/profile_images/1982513791498625024/mTCEFECz_normal.jpg)

Caspar@caspar\_br

A walkthrough of how Managed Deep Agents uses sandbox proxies to keep your credentials safe. [langch.in/mda](https://langch.in/mda)

[🔗 View on Twitter](https://x.com/caspar_br/status/2111133459150512222/video/1)

[🔗 View Quoted Tweet](https://x.com/caspar_br/status/2111133459150512222)

## 视频地址

- [视频 1](https://video.twimg.com/amplify_video/2111132464089616384/vid/avc1/1440x1440/kF18MgnC_IYioBZL.mp4?tag=29)