7.5

CVE-2026-22773

Exploit

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

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.
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Vllm ≫ Vllm Version >= 0.6.4 < 0.12.0
VulnDex Vulnerability Enrichment
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Zu dieser CVE wurde keine Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.4% 0.319
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
nvd@nist.gov 7.5 3.9 3.6
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
security-advisories@github.com 6.5 2.8 3.6
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CWE-770 Allocation of Resources Without Limits or Throttling

The product allocates a reusable resource or group of resources on behalf of an actor without imposing any restrictions on the size or number of resources that can be allocated, in violation of the intended security policy for that actor.

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