Lucene search
K

CVE-2026-22773 vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

🗓️ 10 Jan 2026 06:39:02Reported by GoogleType 
osv
 osv
🔗 osv.dev👁 1 Views

vLLM crashes serving multimodal models with Idefics3 via a crafted 1x1 image, causing server termination; fixed in 0.12.0.

Related
Refs

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation