CVE-2026-12491: Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations

Severity: medium (CVSS 4.8 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.2% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2026-06-17 · updated 2026-07-07
Weakness: CWE-115

Description

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 AI Inference Server: all versions
Red Hat Enterprise Linux AI (RHEL AI) 3: all versions
Red Hat OpenShift AI (RHOAI): all versions
vllm-project vllm: from 0.11.0 before 0.24.0 — fixed in 0.24.0

How to fix

Upgrade to a fixed version: vllm-project vllm 0.24.0. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-12491 or the next vulnerability affects your stack