CVE-2025-68664

Description

LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5.

PUBLISHED Reserved 2025-12-22 | Published 2025-12-23 | Updated 2025-12-24 | Assigner GitHub_M

Problem types

CWE-502: Deserialization of Untrusted Data

Product status

References

github.com/...gchain/security/advisories/GHSA-c67j-w6g6-q2cm exploit

github.com/...gchain/security/advisories/GHSA-c67j-w6g6-q2cm

github.com/langchain-ai/langchain/pull/34455

github.com/langchain-ai/langchain/pull/34458

github.com/...ommit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8

github.com/...ommit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6

github.com/.../langchain/releases/tag/langchain-core==0.3.81

github.com/...i/langchain/releases/tag/langchain-core==1.2.5

cve.org (CVE-2025-68664)

nvd.nist.gov (CVE-2025-68664)

Download JSON

Data based on CVE®. Copyright © 1999-2025, The MITRE Corporation. All rights reserved.