Bug 2438772 (CVE-2026-26013)

Summary: CVE-2026-26013 langchain: SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security DevOps Team <prodsec-dev>
Status: NEW --- QA Contact:
Severity: low Docs Contact:
Priority: low    
Version: unspecifiedCC: anpicker, bparees, dfreiber, drow, dschmidt, erezende, hasun, jburrell, jfula, jkoehler, jlanda, jowilson, jwong, kshier, lphiri, mattdavi, nyancey, omaciel, ometelka, ptisnovs, simaishi, smcdonal, stcannon, syedriko, teagle, ttakamiy, vkumar, xdharmai, yguenane
Target Milestone: ---Keywords: Security
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc Text:
A flaw was found in LangChain. The ChatOpenAI.get_num_tokens_from_messages method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This issue allows an attacker to cause Server-Side Request Forgery (SSRF) by providing malicious image URLs in user input.
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-02-10 23:01:15 UTC
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.