Vulnerability · Published Jan 10, 2026 · Assigned by GitHub_M

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

Medium 6.5

In plain English

A medium-severity resource allocation without limits in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 39% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.5Medium

Exploit odds (30 days)0.4%top 61.4% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.12.0	GHSA-grg2-63fw-f2qr
PyPI	vllm	0.12.0	PYSEC-2026-143

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	>= 0.6.4, < 0.12.0

Weakness: CWE-770 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

References

https://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr x_refsource_CONFIRM