CVE-2025-68665

CRITICALCVSS 9.1/10EPSS 0.75%

Last modified

CVE-2025-68665 is a critical-severity vulnerability rated 9.1/10 on the CVSS scale. LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS's toJSON() method (and subsequently when string-ifying objects using JSON.stringify(). EPSS estimates a 0.75% chance of exploitation in the next 30 days.

Description

LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS's toJSON() method (and subsequently when string-ifying objects using JSON.stringify(). The method did not escape objects with 'lc' keys when serializing free-form data in kwargs. 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 @langchain/core versions 0.3.80 and 1.1.8, and langchain versions 0.3.37 and 1.2.3

Metrics

CVSS 3.1
9.1/10

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

EPSS Probability
0.75%

50.1th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
LangchainLangchain.Js< 0.3.37
LangchainLangchain.Js>= 1.0.0, < 1.2.3
LangchainLangchain\/Core< 0.3.80
LangchainLangchain\/Core>= 1.0.0, < 1.1.8

References

Timeline

Published
Last Modified
Status
Analyzed

Frequently Asked Questions

What is CVE-2025-68665?
LangChain is a framework for building LLM-powered applications. Prior to @langchain/core versions 0.3.80 and 1.1.8, and prior to langchain versions 0.3.37 and 1.2.3, a serialization injection vulnerability exists in LangChain JS's toJSON() method (and subsequently when string-ifying objects using JSON.stringify(). The method did not escape objects with 'lc' keys when serializing free-form data in kwargs. 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 @langchain/core versions 0.3.80 and 1.1.8, and langchain versions 0.3.37 and 1.2.3
How severe is CVE-2025-68665?
CVE-2025-68665 has a CVSS score of 9.1/10 (CRITICAL severity). The EPSS model estimates a 0.75% probability of exploitation in the next 30 days.
How do I fix CVE-2025-68665?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2025-68665?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST