p PatchFirst

CVE-2025-68665

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

This page contains facts from public vulnerability sources. Check the original advisory before updating.

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 8.6 · High · EPSS 0.8% · Fix available

Published
Updated

Stack: node

Affected products and versions

  • langchainjs

    Versions
    • @langchain/core >= 1.0.0, < 1.1.8: Affected
    • @langchain/core < 0.3.80: Affected
    • langchain >= 1.0.0, < 1.2.3: Affected
    • langchain < 0.3.37: Affected

    No fix published

  • @langchain/core npm

    Affected ranges
    • SEMVER: ≥ 1.0.0, < 1.1.8

    Update to 1.1.8

  • @langchain/core npm

    Affected ranges
    • SEMVER: < 0.3.80

    Update to 0.3.80

  • langchain npm

    Affected ranges
    • SEMVER: ≥ 1.0.0, < 1.2.3

    Update to 1.2.3

  • langchain npm

    Affected ranges
    • SEMVER: < 0.3.37

    Update to 0.3.37

Original sources

Check your server →