Read the docs
TI-2026-18291 Aliases CVE-2026-22773GHSA-grg2-63fw-f2qr

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

Priority LOW 33CWE-770Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Impact type
Denial of service
Confidentiality · integrity · availability
None · None · High
Fix status
Partial Red Hat: 3 fixed, 3 without a fix

Attack profile from CVSS 3.1 · NVD. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-770.

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00442 38th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial vllm (vllm-project): 0.12.0vllm (PyPI): 0.12.0Red Hat: 5 advisoriesRed Hat: 3 fixed, 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllm0.6.4 to before 0.12.00.12.0Patch availableCNA
—vllm (PyPI)0.6.4 to before 0.12.00.12.0Patch availableGHSA-grg2-63fw-f2qr
  • vllm Vendorvllm-project Affected 0.6.4 to before 0.12.0 Fixed in 0.12.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected 0.6.4 to before 0.12.0 Fixed in 0.12.0 Patch available GHSA-grg2-63fw-f2qr

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*0.6.4 to before 0.12.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.6.4 to before 0.12.0 Vulnerable ·vLLM

Remediation

  • Fix · CNA vllm (vllm-project) Fixed in 0.12.0
  • Fix · GHSA-grg2-63fw-f2qr vllm (PyPI) Fixed in 0.12.0 Advisory →

Red Hat 5 advisories

  • RHSA-2026:42644 Released 2026-07-21 · Red Hat rating Important
    RHOAI 2.25.9 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 2.25 registry.redhat.io/rhoai/odh-caikit-tgis-serving-rhel9, registry.redhat.io/rhoai/odh-feature-server-rhel9, registry.redhat.io/rhoai/odh-kserve-storage-initializer-rhel9 +36
  • RHSA-2026:30087 Released 2026-06-25 · Red Hat rating Critical
    Red Hat AI Inference Server 3.3.5 (Spyre)
    • Red Hat AI Inference Server 3.3 registry.redhat.io/rhaiis/vllm-spyre-rhel9
  • RHSA-2026:10184 Released 2026-04-23 · Red Hat rating Important
    RHOAI 2.25.5 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 2.25 registry.redhat.io/rhoai/odh-caikit-nlp-rhel9, registry.redhat.io/rhoai/odh-caikit-tgis-serving-rhel9, registry.redhat.io/rhoai/odh-dashboard-rhel9 +47
Show 2 more Red Hat advisories
  • RHSA-2026:3462 Released 2026-02-27 · Red Hat rating Critical
    Red Hat AI Inference Server 3.2.2 (ROCm)
    • Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-rocm-rhel9
  • RHSA-2026:3461 Released 2026-02-27 · Red Hat rating Critical
    Red Hat AI Inference Server 3.2.2 (CUDA)
    • Red Hat AI Inference Server 3.2 registry.redhat.io/rhaiis/vllm-cuda-rhel9

Vendor assessments

Red Hat

Red Hat rating: Moderate. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix yet
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix planned: Out of support scope
Red Hat OpenShift AI (RHOAI)AffectedNo fix planned: Out of support scope
Red Hat AI Inference Server 3.2Fixed RHSA-2026:3461, RHSA-2026:3462
Red Hat AI Inference Server 3.3Fixed RHSA-2026:30087
Red Hat OpenShift AI 2.25Fixed RHSA-2026:10184, RHSA-2026:42644
Not affected: 1 product
  • Red Hat OpenShift AI 2.25

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-22773
  2. 2026-10-03 Alias added: GHSA-grg2-63fw-f2qr
  3. 2026-11-06 Fix available: RHSA-2026:42644 · Red Hat

References

Exploit 1

Advisory 1

Other 4

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences