CVE-2026-44222: Vllm

High severity, CVSS 7.5. EPSS: 0.5% chance of exploitation in the next 30 days.

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.

Affected products

• Vllm Vllm: from 0.6.1, before 0.20.0 (fixed in 0.20.0)

Published 2026-05-12. Last modified 2026-06-17.