Improper Validation of Array Index Affecting tritonserver-backend-vllm-cuda-13.0 package, versions <25.11-r7


Severity

Recommended
0.0
high
0
10

Snyk's Security Team recommends NVD's CVSS assessment. Learn more

Threat Intelligence

EPSS
0.41% (33rd percentile)

Do your applications use this vulnerable package?

In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.

Test your applications
  • Snyk IDSNYK-CHAINGUARDLATEST-TRITONSERVERBACKENDVLLMCUDA130-17117991
  • published2 Jun 2026
  • disclosed12 May 2026

Introduced: 12 May 2026

CVE-2026-44222  (opens in a new tab)
CWE-129  (opens in a new tab)

How to fix?

Upgrade Chainguard tritonserver-backend-vllm-cuda-13.0 to version 25.11-r7 or higher.

NVD Description

Note: Versions mentioned in the description apply only to the upstream tritonserver-backend-vllm-cuda-13.0 package and not the tritonserver-backend-vllm-cuda-13.0 package as distributed by Chainguard. See How to fix? for Chainguard relevant fixed versions and status.

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 Base Scores

version 3.1