AUGUST 4, 2026
Live Feed
Back to database
Case File

CVE-2026-22773

MEDIUM · CVSS 6.5 EPSS 0.40% Public Exploit

Source: NVD + CISA KEV + EPSS (historical backfill) · Published 2026-01-10 · Last synced 2026-08-04

CyberRota Analysis

This is a medium severity vulnerability with a CVSS score of 6.5. Public exploit code or proof-of-concept references have been detected in its references.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

GitHub PoC Links

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-22773
Severity
MEDIUM
CVSS
6.5
EPSS
0.40%

Original NVD Description

vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.

Related CVEs

Other vulnerabilities affecting the same vendor(s)