Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-44843— LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists

Quick assessment

Affected
langchain-ai langchain
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

LangChain是LangChain开源的一个用于开发由大型语言模型 （LLM） 提供支持的应用程序的框架。 LangChain 0.3.85之前版本和1.3.3之前版本存在代码问题漏洞，该漏洞源于运行时代码路径使用过于宽泛的对象白名单反序列化运行输入、输出或其他应用控制的有效载荷，允许攻击者提供的LangChain序列化构造函数字典实例化带有不可信构造函数参数的类。

CVSS 8.2 · High EPSS 0.38% · P30

Possible ATT&CK Techniques 1 AI

T1059 · Command and Scripting Interpreter

Affected Version Matrix 2

VendorProduct Version RangeStatus
langchain-ai langchain < 0.3.85 affected
>= 1.0.0a1, < 1.3.3 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-44843

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
LangChain: Unsafe deserialization of attacker-controlled LangChain objects through overly broad `load()` allowlists
Source: CVE Program / CVE List V5
Vulnerability Description
LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
可信数据的反序列化
Source: CVE Program / CVE List V5
Vulnerability Title
LangChain 代码问题漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
LangChain是LangChain开源的一个用于开发由大型语言模型 （LLM） 提供支持的应用程序的框架。 LangChain 0.3.85之前版本和1.3.3之前版本存在代码问题漏洞，该漏洞源于运行时代码路径使用过于宽泛的对象白名单反序列化运行输入、输出或其他应用控制的有效载荷，允许攻击者提供的LangChain序列化构造函数字典实例化带有不可信构造函数参数的类。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
langchain-ai langchain < 0.3.85 -

II. Public POCs for CVE-2026-44843

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 8242 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2026-44843

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-44843 (1)

IV. Related Vulnerabilities

Same product: langchain
Same vendor: langchain-ai
Same weakness: CWE-502

V. Comments for CVE-2026-44843

No comments yet

Leave a comment