Misinterpretation of Input Affecting vllm-cu130 package, versions <0.24.0-r0


Severity

Recommended
0.0
medium
0
10

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

Threat Intelligence

EPSS
0.24% (15th 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-MINIMOSLATEST-VLLMCU130-17741409
  • published1 Jul 2026
  • disclosed17 Jun 2026

Introduced: 17 Jun 2026

CVE-2026-12491  (opens in a new tab)
CWE-115  (opens in a new tab)

How to fix?

Upgrade Minimos:latest vllm-cu130 to version 0.24.0-r0 or higher.

NVD Description

Note: Versions mentioned in the description apply only to the upstream vllm-cu130 package and not the vllm-cu130 package as distributed by Minimos. See How to fix? for Minimos:latest relevant fixed versions and status.

A flaw was found in vLLM, an open-source library for large language model inference. This vulnerability arises from improper handling of image metadata, specifically EXIF orientation and PNG transparency (tRNS) data, during image processing. When images are converted to RGB, transparency information may be implicitly discarded or remapped, leading to unexpected rendering of transparent pixels and distortion of input content. This can result in the model misinterpreting image content, potentially affecting the integrity of processed data.

CVSS Base Scores

version 3.1