by Kastro CVE-2025-68664
langchain-ai langchain — LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
Description · from the CVE record
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
ProductAffectedFixed inSource
langchain>= 1.0.0, < 1.2.5–CNA
langchain< 0.3.81–CNA
Scores by source
GitHub_M (CNA)9.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
CISA ADPSSVCExploitation: poc · Automatable: yes · Technical impact: partial