Description
LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. 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 versions 0.3.81 and 1.2.5.
Affected products
langchain: langchain core
References8
- github.com/langchain-ai/langchain/security/advisories/GHSA-c67j… ExploitVendor Advisory
- github.com/langchain-ai/langchain/security/advisories/GHSA-c67j… ExploitVendor Advisory
- github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4c… Patch
- github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da7… Patch
- github.com/langchain-ai/langchain/pull/34455 Issue TrackingPatch
- github.com/langchain-ai/langchain/pull/34458 Issue TrackingPatch
- github.com/langchain-ai/langchain/releases/tag/langchain-core%3… Release Notes
- github.com/langchain-ai/langchain/releases/tag/langchain-core%3… Release Notes
Metrics
- CVSS 3.1
-
8.2
HIGH
Score source: NVD
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N - EPSS — exploit probability
- 43% percentile: 99 · as of 11 November 2026
- CWE
- CWE-502
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.