CVE-2026-44843

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.
References
Configurations

Configuration 1 (hide)

OR cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*
cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*

History

29 May 2026, 19:48

Type Values Removed Values Added
First Time Langchain
Langchain langchain
CPE cpe:2.3:a:langchain:langchain:*:*:*:*:*:*:*:*
References () https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724 - () https://github.com/langchain-ai/langchain/security/advisories/GHSA-pjwx-r37v-7724 - Mitigation, Vendor Advisory

26 May 2026, 21:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-05-26 21:16

Updated : 2026-05-29 19:48


NVD link : CVE-2026-44843

Mitre link : CVE-2026-44843

CVE.ORG link : CVE-2026-44843


JSON object : View

Products Affected

langchain

  • langchain
CWE
CWE-502

Deserialization of Untrusted Data