Serialization Injection in LangChain JS toJSON() Method

Publication date: 2025-12-23

Last updated on: 2025-12-23

Assigner: GitHub, Inc.

Description

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

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2025-12-23

Last Modified

2025-12-23

Generated

2026-07-06

AI Q&A

2025-12-24

EPSS Evaluated

2026-07-05

NVD

CVE-2025-68665

Affected Vendors & Products

Vendor	Product	Version / Range
langchain	core	0.3.80
langchain	langchain	1.2.3
langchain	core	1.1.8
langchain	langchain	0.3.37

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-502	The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.

Attack-Flow Graph

Executive Summary

This vulnerability is a serialization injection issue in LangChain JS's toJSON() method. The method did not properly escape objects with 'lc' keys when serializing free-form data in keyword arguments. Since the 'lc' key is used internally by LangChain to mark serialized objects, user-controlled data containing this key structure could be treated as legitimate LangChain objects during deserialization instead of plain user data, potentially allowing injection of malicious serialized objects.

Impact Analysis

This vulnerability can impact you by allowing an attacker to inject malicious serialized objects during deserialization, which could lead to unauthorized actions or compromise of the application using LangChain. The CVSS score of 8.6 indicates a high severity with network attack vector and no user interaction required, potentially leading to high confidentiality impact.

Mitigation Strategies

Update @langchain/core to version 0.3.80 or 1.1.8 or later, and update langchain to version 0.3.37 or 1.2.3 or later, as these versions contain the patch that fixes the serialization injection vulnerability in the toJSON() method.

Hi! I’m here to help you understand CVE-2025-68665. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70