CVE-2025-68665

LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS's toJSON() method (and subsequently when string-ifying objects using JSON.stringify(). The method did not escape objects with 'lc' keys when serializing free-form data in kwargs. 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 @langchain/core versions 0.3.80 and 1.1.8, and langchain versions 0.3.37 and 1.2.3
Configurations

Configuration 1 (hide)

OR cpe:2.3:a:langchain:langchain.js:*:*:*:*:*:*:*:*
cpe:2.3:a:langchain:langchain.js:*:*:*:*:*:*:*:*
cpe:2.3:a:langchain:langchain\/core:*:*:*:*:*:node.js:*:*
cpe:2.3:a:langchain:langchain\/core:*:*:*:*:*:node.js:*:*

History

No history.

Information

Published : 2025-12-23 23:15

Updated : 2026-01-13 16:17


NVD link : CVE-2025-68665

Mitre link : CVE-2025-68665

CVE.ORG link : CVE-2025-68665


JSON object : View

Products Affected

langchain

  • langchain\/core
  • langchain.js
CWE
CWE-502

Deserialization of Untrusted Data