CVE-2026-12491: Red Hat Ai Inference Server

Medium severity, CVSS 4.8. EPSS: 0.2% chance of exploitation in the next 30 days.

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.

Affected products

• Red Hat Red Hat Ai Inference Server
• Red Hat Red Hat Enterprise Linux Ai Rhel Ai 3
• Red Hat Red Hat Openshift Ai Rhoai
• Vllm-Project Vllm: from 0.11.0, before 0.24.0 (fixed in 0.24.0)

Published 2026-06-17. Last modified 2026-07-07.