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: 2026-05-12
Score: 6.5 Medium
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-hpv8-x276-m59f vLLM Vulnerable to Remote DoS via Special-Token Placeholders
History

Thu, 14 May 2026 15:45:00 +0000

Type Values Removed Values Added
First Time appeared Vllm
Vllm vllm
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Vendors & Products Vllm
Vllm vllm

Wed, 13 May 2026 13:15:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}


Tue, 12 May 2026 23:00:00 +0000

Type Values Removed Values Added
First Time appeared Vllm-project
Vllm-project vllm
Vendors & Products Vllm-project
Vllm-project vllm

Tue, 12 May 2026 20:15:00 +0000

Type Values Removed Values Added
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.
Title vLLM: Remote DoS via Special-Token Placeholders
Weaknesses CWE-129
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}


cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-05-13T12:24:53.560Z

Reserved: 2026-05-05T15:42:40.518Z

Link: CVE-2026-44222

cve-icon Vulnrichment

Updated: 2026-05-13T12:24:49.160Z

cve-icon NVD

Status : Analyzed

Published: 2026-05-12T20:16:43.160

Modified: 2026-05-14T15:38:19.560

Link: CVE-2026-44222

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-05-12T22:45:15Z

Weaknesses