CVE Database · CVE-2026-44222
CVSS v3.1
6.5
EPSS
0.41%
Published
May 12, 2026
Modified
May 14, 2026
Public PoC / Exploit (1)
All weaponized →Links to public security research (Exploit-DB, Nuclei, Trickest, GitHub) for defensive use only.
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 Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:HWeaknesses (CWE)
Affected Products (1)
References (2)