CVE-2026-26013
LOWlangchain-core < 1.2.11 - Server-Side Request Forgery via ChatOpenAI Image URL
Title source: llmDescription
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.
References (3)
Core 3
Core References
Vendor Advisory x_refsource_confirm
https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r
Patch x_refsource_misc
https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565
Release Notes x_refsource_misc
https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11
Scores
CVSS v3
3.7
EPSS
0.0002
EPSS Percentile
5.6%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L
CISA SSVC
Vulnrichment
Exploitation
none
Automatable
no
Technical Impact
partial
Details
CWE
CWE-918
Status
published
Products (3)
langchain/langchain_core
< 1.2.11
langchain-ai/langchain
< 1.2.11
pypi/langchain-core
0 - 1.2.11PyPI
Published
Feb 10, 2026
Tracked Since
Feb 18, 2026