cve.bz

CVE-2025-68664 langchain langchain core: Deserialization of Untrusted Data

8.2 highExploitEPSS 43%Fix available

High (8.2) in langchain langchain core. EPSS 43% estimated probability of exploitation activity in the next 30 days. Fixed in langchain-core 0.3.81, 1.2.5.

On this page
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.

Severity

CVSS 3.1

8.2 high
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
EPSS
43% (unchanged from 43% a week ago; 43% 30 days ago) estimated probability of exploitation activity in the next 30 days; 99th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: yes · Technical impact: partial, assessed 2025-12-24. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-502 Deserialization of Untrusted Data
OWASP Top 10
A08:2025 Software or Data Integrity Failures
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2025-68664 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2025-68664?via=ask-ai-copy and https://cve.bz/cve/CVE-2025-68664?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2025-68664 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
langchain:langchain_corebefore 0.3.81
langchain:langchain_corefrom 1.0.0 before 1.2.5

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-c67j-w6g6-q2cmPyPIlangchain-core>=1.0.0 <1.2.51.2.5
GHSA-c67j-w6g6-q2cmPyPIlangchain-core<0.3.810.3.81
PYSEC-2026-373PyPIlangchain-core<0.3.81
>=1.0.0 <1.2.5
0.3.81, 1.2.5

Red Hat

Red Hat rates this Critical.

Red Hat's statement

This vulnerability is rated Critical for Red Hat products. A serialization injection flaw in LangChain's `dumps()` and `dumpd()` functions allows remote attackers to achieve arbitrary code execution. This occurs when user-controlled data containing the internal 'lc' key is improperly deserialized as a legitimate LangChain object.

ProductPackageStateAdvisory
Red Hat Ansible Automation Platform 2.4ansible-automation-platform-24/lightspeed-rhel8:1767342459Fixed 2026-01-08RHSA-2026:0406
Red Hat Ansible Automation Platform 2.5ansible-automation-platform-25/lightspeed-chatbot-rhel8:1767224443Fixed 2026-01-08RHSA-2026:0409
Red Hat Ansible Automation Platform 2.5ansible-automation-platform-25/lightspeed-rhel8:1767216121Fixed 2026-01-08RHSA-2026:0409
Red Hat Ansible Automation Platform 2.6ansible-automation-platform-26/lightspeed-rhel9:1767625654Fixed 2026-01-08RHSA-2026:0408
Red Hat OpenShift Lightspeed 1.1.5openshift-lightspeed/lightspeed-service-api-rhel9:1769058587Fixed 2026-01-30RHSA-2026:1610
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/de-minimal-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/de-minimal-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/de-supported-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/de-supported-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/ee-minimal-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/ee-minimal-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/ee-supported-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/ee-supported-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/platform-resource-runner-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/aap-cloud-metrics-collector-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/ansible-dev-tools-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/de-minimal-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/de-minimal-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/de-supported-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/de-supported-rhel9Not affected
29 more in the JSON and on Red Hat's page.

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2025-68664.

Public exploits

GitHub PoC

Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it. How Harbor Check reads them, and what it found.

Attack patterns (CAPEC)

  • CAPEC-586 Object Injection Likelihood: Medium · Severity: High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON