Log in Start free

Vulnerability · Published Jun 17, 2026 · Assigned by redhat

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

Medium 4.8

In plain English

A medium-severity security flaw in Red Hat AI Inference Server from Red Hat. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 15% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)4.8Medium
Exploit odds (30 days)0.2%top 84.9% of all CVEs
Exploited in the wildNo reportsCISA SSVC: none
Attack toolingNoneno public tooling known

Official 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 packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIvllm0.24.0GHSA-8jr5-v98p-w75m
PyPIvllmno fix listedPYSEC-2026-3406

Affected products (as reported)

VendorProductVersions
vllm-project vLLM 0.11.0 – before 0.24.0
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat AI Inference Server see references
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 see references
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 see references
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 see references
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 see references
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 see references
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 see references
Red Hat Red Hat Enterprise Linux AI (RHEL AI) 3 see references
Red Hat Red Hat OpenShift AI (RHOAI) see references
Red Hat Red Hat OpenShift AI (RHOAI) see references
Red Hat Red Hat OpenShift AI (RHOAI) see references
Red Hat Red Hat OpenShift AI (RHOAI) see references
Red Hat Red Hat OpenShift AI (RHOAI) see references
Red Hat Red Hat OpenShift AI (RHOAI) see references
Red Hat Red Hat OpenShift AI (RHOAI) see references
Red Hat Red Hat OpenShift AI (RHOAI) see references

Weakness: CWE-115 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L

References