Skip to content
Fencer Vulns
low 3.7

CVE-2026-26013 json

LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages

published 2026-02-10 8 mo ago modified 2026-09-10 1 mo ago also EUVD-2026-6240 , GHSA-2g6r-c272-w58r , PYSEC-2026-2562

cvss
3.7
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 36%
public exploits
0
none known

Summary

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability is fixed in 1.2.11.

Patch / fix

  • pypi langchain-core 1.2.11
  • langchain langchain_core 1.2.11

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-2026-26013 updated cvss 3.7

langchain: SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages

  • Red Hat OpenShift Lightspeed openshift-lightspeed/lightspeed-service-api-rhel9 Red Hat Ansible Automation Platform 2 ansible-automation-platform-24/lightspeed-rhel8, ansible-automation-platform-25/lightspeed-rhel8, ansible-automation-platform-26/lightspeed-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-llama-stack-core-rhel9, rhoai/odh-trustyai-ragas-lls-provider-dsp-rhel9
    affected: workaround, no fix available “Fix deferred”

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

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
8 mo ago

Exploit prediction

0.42% chance of exploitation in the next 30 days, higher than 36% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 3.7 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
GitHub 3.1 3.7 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
OSV 3.1 3.7 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L

Affected packages

ecosystem package affected fixed in
pypi langchain-core
<1.2.11
1.2.11

Affected products

  • langchain-ai langchain

Classification

Weakness
  • CWE-918 Server-Side Request Forgery

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.