Skip to content
LLMHigh

CVE-2026-44222: vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.…

Occurred
May 12, 2026
Published
May 12, 2026
Source
NVD CVE

Summary

vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.

Tags

  • CVE
  • CVE-2026-44222
  • cvss:MEDIUM

Classification

Category confidence: 95%
Severity confidence: 90%

Rationale: CVE describes a token injection vulnerability in vLLM LLM serving engine causing worker termination and availability degradation.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source