Log in Start free

Vulnerability · Published Dec 23, 2025 · Assigned by GitHub_M

CVE-2025-68665LangChain serialization injection vulnerability enables secret extraction

High 8.6

In plain English

A high-severity unsafe deserialization in langchainjs from langchain-ai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.8% (higher than 57% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)8.6High
Exploit odds (30 days)0.8%top 43.5% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official 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

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
npm@langchain/core1.1.8GHSA-r399-636x-v7f6
npm@langchain/core0.3.80GHSA-r399-636x-v7f6
npmlangchain1.2.3GHSA-r399-636x-v7f6
npmlangchain0.3.37GHSA-r399-636x-v7f6

Affected products (as reported)

VendorProductVersions
langchain-ai langchainjs @langchain/core >= 1.0.0, < 1.1.8@langchain/core < 0.3.80langchain >= 1.0.0, < 1.2.3langchain < 0.3.37

Weakness: CWE-502 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N

References