Skip to content
Fencer Vulns
critical 9.3

CVE-2025-68664 in the critical feed json

LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

published 2025-12-23 10 mo ago modified 2026-10-27 12 d ago also EUVD-2025-204849 , GHSA-c67j-w6g6-q2cm , PYSEC-2026-373

cvss
9.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
42.9%
EPSS 42.9% chance of exploitation in 30 days, percentile 98%
public exploits
1
Exploit-DB

Summary

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.

Patch / fix

  • pypi langchain-core 0.3.81, 1.2.5
  • langchain langchain_core 0.3.81, 1.2.5

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2025-68664 updated cvss 9.3

langchain-core: LangChain: Arbitrary code execution via serialization injection

  • Red Hat Ansible Automation Platform 2.4 ansible-automation-platform-24 1767342459
    fixed: vendor fix RHSA-2026:0406
  • Red Hat Ansible Automation Platform 2.5 ansible-automation-platform-25 1767216121, ansible-automation-platform-25 1767224443
    fixed: vendor fix RHSA-2026:0409
  • Red Hat Ansible Automation Platform 2.6 ansible-automation-platform-26 1767625654
    fixed: vendor fix RHSA-2026:0408
  • Red Hat OpenShift Lightspeed 1.1.5 openshift-lightspeed 1769058587
    fixed: vendor fix RHSA-2026:1610
  • Red Hat Ansible Automation Platform 2 ansible-automation-platform/ee-minimal-rhel8, ansible-automation-platform/ee-minimal-rhel9, ansible-automation-platform-26/mcp-tools-rhel9, ansible-automation-platform-24/de-minimal-rhel8, ansible-automation-platform-24/de-minimal-rhel9, ansible-automation-platform-24/ee-minimal-rhel8, +26 more Red Hat Ansible Automation Platform 2.4 ansible-automation-platform 1767615136, ansible-automation-platform 1767615183 Red Hat Ansible Automation Platform 2.5 ansible-automation-platform 1767608947, ansible-automation-platform 1767608959, ansible-automation-platform-25 1765858554, ansible-automation-platform-25 1765858670, ansible-automation-platform-25 1765859003, ansible-automation-platform-25 1765859133, +20 more Red Hat Ansible Automation Platform 2.6 ansible-automation-platform 1767630589, ansible-automation-platform 1767630618, ansible-automation-platform-26 1765586332, ansible-automation-platform-26 1765586806, ansible-automation-platform-26 1765587094, ansible-automation-platform-26 1765587912, +21 more Red Hat Enterprise Linux AI (RHEL AI) rhelai1/bootc-amd-rhel9, rhelai1/bootc-intel-rhel9, rhelai1/bootc-nvidia-rhel9, rhelai1/bootc-azure-amd-rhel9, rhelai1/instructlab-amd-rhel9, rhelai1/bootc-aws-nvidia-rhel9, +4 more
    not affected: vulnerable code not present
  • Red Hat OpenShift AI (RHOAI) rhoai/odh-llama-stack-core-rhel9, rhoai/odh-trustyai-ragas-lls-provider-dsp-rhel9
    not affected: vulnerable code not in execute path
  • Red Hat OpenShift Lightspeed 1.1.5 openshift-lightspeed 1769584348, openshift-lightspeed 1769752297, openshift-lightspeed 1769776075, openshift-lightspeed 1769778589, openshift-lightspeed 1769780437
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

Timeline

  1. Published
  2. First public exploit (EDB-52514)

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
10 mo ago

Exploit prediction

42.93% chance of exploitation in the next 30 days, higher than 98% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • EDB-52514 LangChain Core 1.2.4 - SSTI/RCE webapps, 2026-04-29
  • github.com https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 9.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
GitHub 3.1 9.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
NVD 3.1 8.2 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
OSV 3.1 9.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N

Affected packages

ecosystem package affected fixed in
pypi langchain-core
>=1.0.0, <1.2.5
<0.3.81
1.2.5
0.3.81

Affected products

  • langchain-ai langchain

Classification

Weakness
  • CWE-502 Deserialization of Untrusted Data

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.