CVE-2026-12491
Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
Using Red Hat AI Inference Server by Red Hat?
Get instant alerts when new vulnerabilities affect Red Hat AI Inference Server - before attackers find them.
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
Our own answer: ranges merged, affected separated from platform-only, with confidence and review flags.
Remediation
No guide yetNo remediation guidance has been written for this CVE yet, and no fixed version or vendor advisory is recorded against it.
References (2)
SSVC — Action Prioritization
SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.
CVSS
- Attack Vector
- NETWORK
- Complexity
- HIGH
- Privileges
- NONE
- User Interaction
- NONE
- Scope
- UNCHANGED
- Confidentiality
- NONE
- Integrity
- LOW
- Availability
- LOW
Quick Info
Get alerted
Stop reading CVE feeds looking for your own stack
Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.