LangChain serialization injection vulnerability enables secret extraction - @langchain/core

Description

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.

Recommendation

Update the @langchain/core package to the latest compatible version. Followings are version details:

• Affected version(s): **< 0.3.80

  >= 1.0.0, < 1.1.8**

• Patched version(s): **0.3.80

  1.1.8**

References

• GHSA-r399-636x-v7f6
• CVE-2025-68665
• CWE-502
• CAPEC-310
• OWASP 2021-A6
• OWASP 2021-A8

Related Issues

• LangChain serialization injection vulnerability enables secret extraction - CVE-2025-68665
• systeminformation has a Command Injection vulnerability in fsSize() function on Windows - CVE-2025-68154
• @perfood/couch-auth has a host header injection vulnerability - CVE-2025-70948
• pg-promise SQL Injection vulnerability - CVE-2025-29744

You might also like:

How do hackers hack websites?

These 7 PHP mistakes leave your website open to the hackers

Exploiting Server Version Disclosure

Tags:

npm

@langchain/core