研究人员在流行的开源框架LangChain中发现一个关键漏洞，该框架广泛用于驱动大型语言模型（LLM）Agent。该漏洞编号为CVE-2025-68664，CVSS评分高达9.3分，攻击者可能利用该漏洞提取敏感环境变量或触发非预期的系统操作。 漏洞根源：数据序列化缺陷 该漏洞源于 ...

Would you trust an AI agent to run unverified code on your system? For developers and AI practitioners, this question isn’t just hypothetical—it’s a critical challenge. The risks of executing ...

重写 LangChain 之后，Agent 开发终于告别“拼凑学”。 本周，LangChain 宣布完成 1.25 亿美元融资，投后估值 12.5 亿美元。除了宣布其独角兽地位外，该公司还发布了里程碑式更新：经过 3 年迭代，LangChain 1.0 正式登场。而且，这并非一次常规的版本升级，而是一场从 ...

A new report out today from artificial intelligence security startup Cyata Security Ltd. details a recently uncovered critical vulnerability on langchain-core, the foundational library behind ...

LangChain is one of the hottest development platforms for creating applications that use generative AI—but it’s only available for Python and JavaScript. What to do if you’re an R programmer who wants ...

in this video I'll be showing you how to build your own custom AI agent using Lang chain and retrieval augmented generation now we'll build this out using Python and even if you're just an ...