LangChain serialization injection vulnerability enables secret extraction (GHSA-r399-636x-v7f6)

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

• Lobe Chat affected by Cross-Site Scripting(XSS) that can escalate to Remote Code Execution(RCE) - CVE-2026-23733
• Websites were able to send any requests to the development server and read the response in vite - CVE-2025-24010
• Parsed HTML anchor links in Markdown provided to parseMarkdown can result in XSS in @nuxtjs/mdc - CVE-2025-24981
• Babel vulnerable to arbitrary code execution when compiling specifically crafted malicious code - CVE-2023-45133

Tags:

npm

@langchain/core