---
id: 20260318-T0-10
title: "LangSmith推出沙箱环境，安全执行Agent代码"
title_en: "LangSmith Sandboxes Enable Secure Agent Code Execution"
url: https://ai.daily.yangsir.net/daily/20260318-T0-10
issue_date: 2026-03-18
publish_date: 2026-03-17T15:51:07.000Z
category: tools
source_name: "LangChain Blog"
source_url: https://blog.langchain.com/introducing-langsmith-sandboxes-secure-code-execution-for-agents/
---

# LangSmith推出沙箱环境，安全执行Agent代码

LangChain发布LangSmith沙箱功能，开发者可通过单行代码创建隔离环境安全执行Agent代码。目前处于私有预览阶段，将为AI应用提供更安全的代码运行环境，防止恶意代码执行和数据泄露风险。

## English Version

**LangSmith Sandboxes Enable Secure Agent Code Execution**

LangChain has released LangSmith Sandboxes, allowing developers to create isolated environments for secure agent code execution with a single line of code. Currently in private preview, the feature provides a safer runtime environment for AI applications, preventing malicious code execution and data breaches.

---

**来源**：[LangChain Blog](https://blog.langchain.com/introducing-langsmith-sandboxes-secure-code-execution-for-agents/)

**详情页**：https://ai.daily.yangsir.net/daily/20260318-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*