← Vulnerability feed

Vulnerability record · CVE-2025-68664 · published 23 December 2025

CVE-2025-68664: Langchain core deserialization of untrusted data vulnerability

Langchain · Langchain Core

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.

8.2 CVSS 3.1 High EPSS 43% · top 1.3% CWE-502 · Deserialization of untrusted data
8.2CVSS 3.1 base score
43%EPSS exploitation probability, 30 days
NoNot in CISA KEV
1Affected product versions listed by NVD
8References, 2 tagged exploit
17 Jun 2026Last modified by NVD

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.

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

Affected products

1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.

References

LinkTags
https://github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8 Patch
https://github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6 Patch
https://github.com/langchain-ai/langchain/pull/34455 Issue TrackingPatch
https://github.com/langchain-ai/langchain/pull/34458 Issue TrackingPatch
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.81 Release Notes
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.5 Release Notes
https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm ExploitVendor Advisory
https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm ExploitVendor Advisory

Track CVE-2025-68664 inside VULONE

Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.

Start free Open in platform

Related vulnerabilities

Same products first, then exploited flaws of the same weakness class.

7.5CVE-2026-34070Langchain core path traversal vulnerabilityLangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.load…EPSS 1.2%5.3CVE-2026-40087Langchain core vulnerabilityLangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain's f-string prompt-template validatio…EPSS 0.45%3.7CVE-2026-26013Langchain core server-side request forgery (ssrf) vulnerabilityLangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetc…EPSS 0.42%9.8CVE-2021-23758Ajax.NET Professional ajaxpro.2 untrusted deserialization RCEAll versions of the ajaxpro.2 package (Ajax.NET Professional) deserialize untrusted data and permit deserialization of arbitrary .NET classes. That l…KEVEPSS 83%analysed9.8CVE-2026-63077JetBrains TeamCity unauthenticated RCE via agent polling deserializationJetBrains TeamCity before 2026.1.3 and 2025.11.7 deserializes untrusted data received through the agent polling protocol, allowing unauthenticated re…KEVEPSS 9.8%analysed9.8CVE-2026-50522Microsoft SharePoint deserialization flaw allows remote code executionMicrosoft SharePoint Server deserializes untrusted data, letting an unauthorized attacker run code over the network. The flaw is remotely reachable w…KEVEPSS 3.0%analysed9.8CVE-2026-58644Microsoft SharePoint deserialization flaw allows remote code executionMicrosoft SharePoint Server deserializes untrusted data, letting an unauthenticated network attacker execute code. The flaw is rated CVSS 9.8 critica…KEVEPSS 16%analysed8.8CVE-2026-45659Microsoft SharePoint Server deserialization flaw enables remote code executionMicrosoft SharePoint Server deserializes untrusted data, letting an authenticated attacker run code over the network. The flaw is remotely reachable,…KEVEPSS 2.7%analysed

Source: NIST National Vulnerability Database (record CVE-2025-68664), CISA KEV, FIRST EPSS (scores of 2026-09-26). This page is refreshed as NVD updates the record.