CVE-2026-44222

vLLM: Remote DoS via Special-Token Placeholders

Published May 12, 2026 CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

vLLM, an inference engine for large language models, contains a token injection flaw in its multimodal processing from version 0.6.1 up to 0.19.x. When an unauthenticated prompt includes special tokens that map to image or video placeholder sequences that lack actual data, the engine attempts to index into empty grids. This raises an unhandled IndexError, causing the worker to crash or become unavailable, thereby denying service to legitimate users. The flaw is a classic example of CWE‑129, improper validation of array indices.

Affected Systems

Vendors affected are the vllm‑project, specifically the vLLM inference and serving engine. Any deployments using vLLM versions between 0.6.1 inclusive and before 0.20.0 are susceptible. The vulnerability impacts multimodal paths that utilize image_grid_thw or video_grid_thw components.

Risk and Exploitability

The CVSS score of 6.5 indicates a moderate to high severity, while the EPSS score is not available, suggesting no public exploitation data. The flaw is not currently listed in CISA’s KEV catalog. Attackers can exploit the vulnerability remotely by sending a crafted text prompt containing the special token placeholders to an exposed vLLM endpoint. No authentication is required, making any publicly reachable instance a potential target. Successful exploitation would result in worker termination or degraded availability until the service is restarted.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade vLLM to version 0.20.0 or later, where the placeholder handling has been fixed.
  • If upgrading is not immediately possible, disable multimodal processing that relies on image_grid_thw or video_grid_thw or reject prompts containing the vulnerable special token placeholders.
  • Implement input validation to reject or sanitize special token placeholders before they reach the processing layer.
  • Monitor the service for IndexError logs and restart workers automatically to mitigate temporary availability loss.

Generated by OpenCVE AI on May 12, 2026 at 21:41 UTC.

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

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

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

Weaknesses
  • CWE-129

    Improper Validation of Array Index

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
May 13, 2026, 12:24 PM
Reserved
May 5, 2026, 3:42 PM
Status
Analyzed
Published
May 12, 2026, 8:16 PM
Modified
Nov 11, 2026, 8:10 PM