Information Exposure Through Log Files Affecting tritonserver-backend-vllm-cuda-13.0 package, versions <25.11-r2


Severity

Recommended
low

Based on default assessment until relevant scores are available.

Threat Intelligence

Exploit Maturity
Proof of Concept
EPSS
3.72% (89th 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-TRITONSERVERBACKENDVLLMCUDA130-15855795
  • published31 Mar 2026
  • disclosed2 Feb 2026

Introduced: 2 Feb 2026

CVE-2026-22778  (opens in a new tab)
CWE-532  (opens in a new tab)

How to fix?

Upgrade Chainguard tritonserver-backend-vllm-cuda-13.0 to version 25.11-r2 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 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.