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.
Metrics
CVSS 3.1 8.2/10
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:NWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| langchain-ai | langchain | >= 1.0.0, < 1.2.5; < 0.3.81 |
References
- https://github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8Patch
- https://github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6Patch
- https://github.com/langchain-ai/langchain/pull/34455Issue Tracking, Patch
- https://github.com/langchain-ai/langchain/pull/34458Issue Tracking, Patch
- https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.81Release Notes
- https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.5Release Notes
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cmExploit, Vendor Advisory
- https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cmExploit, Vendor Advisory
Timeline
- Published
- Dec 23, 2025
- Last modified
- Oct 19, 2026
- NVD status
- Analyzed