Skip to content
Fencer Vulns
medium 6.5

CVE-2026-22773 json

vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

published 2026-01-10 9 mo ago modified 2026-09-10 1 mo ago also EUVD-2026-1865 , GHSA-grg2-63fw-f2qr , PYSEC-2026-143

cvss
6.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 38%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi vllm 0.12.0
  • vllm-project vllm 0.12.0
  • vllm vllm 0.12.0

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-22773 updated cvss 6.5

vllm: vLLM: Denial of Service via specially crafted image in multimodal model serving

  • Red Hat AI Inference Server rhaiis/vllm-tpu-rhel9
    affected: workaround, no fix available
  • Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-aws-cuda-rhel9, rhelai3/bootc-gcp-cuda-rhel9, rhelai3/bootc-azure-cuda-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-vllm-gaudi-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-storage-initializer-rhel9
    affected: workaround, no fix planned “Out of support scope”
  • Red Hat AI Inference Server 3.2 rhaiis 1772160593, rhaiis 1772160625
    fixed: vendor fix RHSA-2026:3461
  • Red Hat AI Inference Server 3.3 rhaiis/vllm-spyre-rhel9 1782352919
    fixed: vendor fix RHSA-2026:30087
  • Red Hat OpenShift AI 2.25 rhoai 1776259063, rhoai/odh-vllm-cuda-rhel9 1783998774, rhoai/odh-vllm-rocm-rhel9 1783998857
    fixed: vendor fix RHSA-2026:10184
  • Red Hat OpenShift AI 2.25 rhoai 1775144403, rhoai 1776243157, rhoai 1776243163, rhoai 1776243192, rhoai 1776243217, rhoai 1776243229, +144 more
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
9 mo ago

Exploit prediction

0.44% chance of exploitation in the next 30 days, higher than 38% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
GitHub 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
NVD 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
OSV 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Affected packages

ecosystem package affected fixed in
pypi vllm
>=0.6.4, <0.12.0
0.12.0

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-770 Allocation of Resources Without Limits or Throttling

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.