Skip to content
OpenAdvisories
Medium WID-SEC-2026-1992 1 CVE

vllm: Schwachstelle ermöglicht Manipulation von Daten

Published Jun 17, 2026 · Updated Jun 17, 2026 · de-DE

Platform: Linux

Summary

Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um Daten zu manipulieren.

Product

Open Source vLLM ist eine Open-Source-Bibliothek für schnelle und effiziente Inferenz von Large Language Models (LLMs).

Vulnerabilities 1

  • Medium 4.8
    CVE-2026-12491

    Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations

    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 c…

    Red Hat vLLM vLLM Red Hat OpenShift AI (RHOAI) Linux PyPI

Revision history

  1. #1

    Initiale Fassung

References