Deserialization in Langchain Core

CVE-2025-68664

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.

Vulnerability class: Insecure Deserialization

Published · last modified .

CVSS v3 metric

CVSS v3 base score 9.3 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N.

EPSS exploit prediction

EPSS: 0.429 (98.7th percentile), scored .

Moderate probability of exploitation in the next 30 days — watch for active exploitation reports. 99th percentile — 98.7% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2025-68664: held from 0.434 to 0.429.

EPSS over last 30 days · oldest: 0.434 · newest: 0.429 · change: -0.005

Affected products

Weakness classification (CWE)

Public proof-of-concept exploits

References

Frequently asked questions

What is CVE-2025-68664?
CVE-2025-68664 is a critical-severity vulnerability in Langchain Core, classified under Deserialization of Untrusted Data. CVSS score: 9.3/10. Published 2025-12-23.
How severe is CVE-2025-68664?
Critical severity. CVSS v3 base score is 9.3 out of 10.
Is CVE-2025-68664 known to be exploited?
3 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.