Skip to main content
Public proof of conceptFix available

CVE-2025-68664

A public proof of concept exists; no exploitation attested.

  • Published2025-12-23
  • Fixed in1.2.5 · 0.3.81
  • WeaknessCWE-502

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

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.

Timeline

dates in UTC
  1. 2025-12-2323:15CVE publishedNVD
  2. 2026-04-29Exploit-DB entryExploit-DB

Versions per branch

NVD · OSV
Langchain langchain core
BranchAffectedFixed in
1.x≥ 1.0.0, < 1.2.51.2.5
0.3< 0.3.810.3.81

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Products declared by the CNA1 product

As GitHub_M, the CNA that assigned this CVE, declared them in the CVE record; versions as written.

  • langchain-ai langchain
    Affected
    • = >= 1.0.0, < 1.2.5no fix stated
    • = < 0.3.81no fix stated

Source: the CNA record (CVE Program), © The MITRE Corporation,CVE Terms of UseCVE recordupdated 2025-12-23

Distribution builds and vendor advisories

Packages from OSV.dev and products from the vendors' CSAF advisories.

version not verifiedVersions not verified: read as OSV.dev and the vendors publish them, not checked against each vendor's release list.

Packages

  • langchain-coreRoot:PyPIall versions · fixed in 0.3.72+aikido.2
  • langchain-coreRoot:PyPIall versions · fixed in 0.3.72+aikido.3
  • langchain-coreRoot:PyPIall versions · fixed in 0.3.72+aikido.4
  • langchain-coreRoot:PyPIall versions · fixed in 0.3.78+aikido.2
  • langchain-coreRoot:PyPIall versions · fixed in 1.0.2+aikido.4
  • langchain-coreRoot:PyPIall versions · fixed in 1.0.2+aikido.5
  • langchain-coreRoot:PyPIall versions · fixed in 1.2.0+aikido.2
  • langchain-coreRoot:PyPIall versions · fixed in 1.2.4+aikido.5

15 more package ranges on OSV.dev

Vendor advisories

  • CVE-2025-68664 Red Hat Product Security18 products fixed

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

  • RHSA-2026:1610 Red Hat Product Security2 products fixed

    Red Hat Security Advisory: Red Hat OpenShift Lightspeed 1.0.9 security update

  • RHSA-2026:0409 Red Hat Product Security8 products fixed

    Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.5 Container Release Update

  • RHSA-2026:0408 Red Hat Product Security4 products fixed

    Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.6 Container Release Update

  • RHSA-2026:0406 Red Hat Product Security4 products fixed

    Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.4 Container Release Update

Full record on NVD

Fix

  1. Update Langchain langchain core to 1.2.5 · 0.3.81
  2. Vendor fix Red Hat Product Security RHSA-2026:1610 · 2 productsBefore applying this update, make sure all previously released errata relevant to your system have been applied. For details on how to apply this update, refer to: https://access.redhat.com/articles/11258
  3. Vendor fix Red Hat Product Security RHSA-2026:0409 · 8 productsBefore applying this update, make sure all previously released errata relevant to your system have been applied. For details on how to apply this update, refer to: https://docs.redhat.com/en/documentation/red_hat_ansible_automation_platform/2.5#Upgrading
  4. Vendor fix Red Hat Product Security RHSA-2026:0408 · 4 productsBefore applying this update, make sure all previously released errata relevant to your system have been applied. For details on how to apply this update, refer to: https://docs.redhat.com/en/documentation/red_hat_ansible_automation_platform/2.6#Upgrade
  5. Vendor fix Red Hat Product Security RHSA-2026:0406 · 4 productsBefore applying this update, make sure all previously released errata relevant to your system have been applied. For details on how to apply this update, refer to: https://docs.redhat.com/en/documentation/red_hat_ansible_automation_platform/2.4#Installation%20and%20upgrade

Advisories and patches

Detection

read 2026-11-01 01:02 UTC
Nuclei template
none so far
ProjectDiscovery
Exploit-DB
EDB-52514
Exploit-DB
Proof of concept
Metasploit modules
none listed
Metasploit Framework

Sources

Identifiers

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
Published
2025-12-23
Last Modified
2026-10-19
NVD status
Analyzed
GitHub Advisory
GHSA-c67j-w6g6-q2cm

Frequently asked questions

What is CVE-2025-68664?

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.

Is CVE-2025-68664 actively exploited?

A proof-of-concept exploit exists for CVE-2025-68664, but active exploitation has not been confirmed at this time.

What is the CVSS score for CVE-2025-68664?

CVE-2025-68664 has a CVSS v3 base score of 8.2 (HIGH severity), with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N.

Running langchain-core? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

Get alerts for this productCISA KEV additions, November 2026Search CVEs

No credit card required · No monthly cap on website lookups · 250 API requests/month

Go further

Related vulnerabilities

Same product first, then the same vendor advisory and the same publication week.

Back to CVE Database

Sources for this record