vllm-project · vLLM · published 2026-05-12
CVE-2026-44222vLLM: Remote DoS via Special-Token Placeholders
Routine No exploitation evidence; EPSS 0.4%.
CVE-2026-44222 is not known to be exploited in the wild. EPSS estimates a 0.4% chance of exploitation in the next 30 days, higher than 36% of all CVEs. This vLLM vulnerability: CVSS 6.5 (v3.1). Fixed upstream in vLLM 0.20.0. Routine: patch when convenient.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.20.0.
Patch events
AI toolingvLLM
vLLM security release: 0.20.0
Upgrade to
0.20.0Why: Vendor security release for server software (most severe: CVE-2026-44222).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.4% (37th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 6.5 (v3.1)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA / CISA ADP |
| SSVC exploitation | none | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
>= 0.6.1, < 0.20.0(affected)
Description (from the CVE record)#
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.
Quoted from the CVE Program record.