All vulnerabilities

Servers and applications

CVE-2026-22773

DoS in Idefics3 vision models via image payload with ambiguous dimensions

Severity
High 7.5
Published
9 Jan 2026
Last changed
17 Jun 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.12.0
Exploit chance
0.4% in the next 30 daysHigher than 39% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Allocation without limits (CWE-770)
Attack
Over the network · No login needed · No user action needed
Attacker can
Take it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Also known as
GHSA-grg2-63fw-f2qr
Sources
NVD, Project advisories (GitHub)

Description

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.

The vulnerability is triggered when the image processor encounters a 1x1 pixel image with shape (1, 1, 3) in HWC (Height, Width, Channel) format. Due to the ambiguous dimensions, the processor incorrectly assumes the image is in CHW (Channel, Height, Width) format with shape (3, H, W). This misinterpretation causes an incorrect calculation of the number of image patches, resulting in a fatal tensor split operation failure.

Crash location: vllm/model_executor/models/idefics3.py line 672:

The split() call fails because the computed num_patches value (17) does not match the actual tensor dimension (9):

This unhandled exception terminates the EngineCore process, crashing the server.

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Workarounds

Validating the input:

Managing the exception:

Workarounds as given by vllm-project/vllm's security advisory.

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • From 0.6.4 before 0.12.0
vLLMServers and applications · github:vllm-project/vllm
  • From 0.6.4 before 0.12.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-22773
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-22773
  • GitHub Advisory Database https://github.com/advisories/GHSA-grg2-63fw-f2qr
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr