CVE-2026-26013
LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages
Description
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.
INFO
Published Date :
Feb. 10, 2026, 10:17 p.m.
Last Modified :
Feb. 11, 2026, 3:27 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | LOW | [email protected] | ||||
| CVSS 3.1 | LOW | MITRE-CVE |
Solution
- Update LangChain to version 1.2.11 or later.
- Validate image URLs before processing.
- Implement strict input validation for image URLs.
Public PoC/Exploit Available at Github
CVE-2026-26013 has a 1 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-26013.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-26013 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-26013
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
⚡ Synapse AI — A real-time AI coding assistant built with Django, WebSockets, Gemini 2.0, and MongoDB. Features OTP signup, streaming responses, and session history.
Python CSS JavaScript HTML Procfile
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-26013 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-26013 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Feb. 10, 2026
Action Type Old Value New Value Added Description 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. Added CVSS V3.1 AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L Added CWE CWE-918 Added Reference https://github.com/langchain-ai/langchain/commit/2b4b1dc29a833d4053deba4c2b77a3848c834565 Added Reference https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.11 Added Reference https://github.com/langchain-ai/langchain/security/advisories/GHSA-2g6r-c272-w58r