LangChain serialization injection vulnerability enables secret extraction
langchain-ai langchainjs
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| @langchain/core npm |
|
|
| langchain npm |
|
langchain-ai langchainjs
| Product | Affected | Fixed in |
|---|---|---|
| @langchain/core npm |
|
|
| langchain npm |
|
1.2.30.3.37LangChain 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
From the CVE record · GitHub_M
LangChain JS’s toJSON() does not escape `lc` keys in free-form data, including when objects are serialized with JSON.stringify(). If user-controlled data contains an `lc` key, deserialization can treat it as a LangChain object rather than plain data. The input does not specify network access, authentication, or user-interaction requirements.
Check applications using npm `@langchain/core` versions below 0.3.80 or from 1.0.0 to below 1.1.8, or `langchain` versions below 0.3.37 or from 1.0.0 to below 1.2.3.