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.
Published: 2025-12-23
Score: 9.3 Critical
EPSS: 2.3% Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-c67j-w6g6-q2cm LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
History

Tue, 13 Jan 2026 16:00:00 +0000

Type Values Removed Values Added
First Time appeared Langchain
Langchain langchain Core
CPEs cpe:2.3:a:langchain:langchain_core:*:*:*:*:*:python:*:*
Vendors & Products Langchain
Langchain langchain Core

Fri, 26 Dec 2025 12:15:00 +0000

Type Values Removed Values Added
References
Metrics threat_severity

None

 threat_severity

Critical

Wed, 24 Dec 2025 15:15:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Wed, 24 Dec 2025 12:00:00 +0000

Type Values Removed Values Added
First Time appeared Langchain-ai
Langchain-ai langchain
Vendors & Products Langchain-ai
Langchain-ai langchain

Tue, 23 Dec 2025 23:00:00 +0000

Type Values Removed Values Added
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.
Title LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
Weaknesses CWE-502
References
Metrics cvssV3_1

{'score': 9.3, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N'}

Subscriptions

Langchain Langchain Core
Langchain-ai Langchain
cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2025-12-24T14:40:58.427Z

Reserved: 2025-12-22T23:28:02.917Z

Link: CVE-2025-68664

cve-icon Vulnrichment

Updated: 2025-12-24T14:40:46.764Z

cve-icon NVD

Status : Analyzed

Published: 2025-12-23T23:15:44.933

Modified: 2026-01-13T15:58:23.373

Link: CVE-2025-68664

cve-icon Redhat

Severity : Critical

Publid Date: 2025-12-23T22:47:44Z

Links: CVE-2025-68664 - Bugzilla

cve-icon OpenCVE Enrichment

Updated: 2025-12-24T11:51:55Z

Weaknesses