CVE-2025-68665: LangChain JS serialization injection through toJSON and JSON.stringify

Summary

LangChain JS versions of @langchain/core before 0.3.80 and 1.1.8, and of langchain before 0.3.37 and 1.2.3, contain a serialization injection flaw in the toJSON() method and in JSON.stringify() output. The method does not escape objects carrying the internal 'lc' key when serializing free-form kwargs data. User-controlled input containing that key structure is then treated as a legitimate LangChain object during deserialization instead of plain data.

Mitigation

Fixed in @langchain/core 0.3.80 and 1.1.8, and in langchain 0.3.37 and 1.2.3.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• langchainnpmLLM dependency since 2023-02-14 · 5 tracked dependents
• @langchain/corenpmLLM dependency since 2023-11-22 · 9 tracked dependents

Related items

• MediumGHSA-8prr-f582-jqq3: LangGraph CLI prints the registry push token in `langgraph deploy --verbose` outputSame vendor · GitHub Advisory Database
• HighGHSA-4hm6-w6qq-w73v: LangGraph JavaScript custom authentication may permit cross-user Store accessSame vendor · GitHub Advisory Database
• MediumGHSA-3fx2-cqw9-xr3c: LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requestsSame vendor · GitHub Advisory Database
• MediumGHSA-6hmw-9432-67qq: LangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite storesSame vendor · GitHub Advisory Database
• MediumCVE-2026-108575: BerriAI LiteLLM improper authorization in secret resolution via api_keySame vendor · NVD/CVE Database