SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityAnalyzed

CVE-2026-44222

From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing.

HIGH 7.5EPSS 0.41%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.41%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

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.

CVSS 3.1
7.5 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS
0.41% probability · 35th percentile
CISA KEV
Not listed
Weakness
CWE-129
Affected
vllm/vllm
Source
security-advisories@github.com

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.