Home

Description

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.

PUBLISHED Reserved 2026-05-05 | Published 2026-05-12 | Updated 2026-05-13 | Assigner GitHub_M




MEDIUM: 6.5CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Problem types

CWE-129: Improper Validation of Array Index

Product status

>= 0.6.1, < 0.20.0
affected

References

github.com/...t/vllm/security/advisories/GHSA-hpv8-x276-m59f

github.com/vllm-project/vllm/issues/32656

cve.org (CVE-2026-44222)

nvd.nist.gov (CVE-2026-44222)

Download JSON