CVE-2026-12491
Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
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.
INFO
Published Date :
June 17, 2026, 10:07 a.m.
Last Modified :
June 17, 2026, 10:07 a.m.
Remotely Exploit :
Yes !
Source :
redhat
Affected Products
The following products are affected by CVE-2026-12491
vulnerability.
Even if cvefeed.io is aware of the exact versions of the
products
that
are
affected, the information is not represented in the table below.
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | MEDIUM | 53f830b8-0a3f-465b-8143-3b8a9948e749 |
Solution
- Update vLLM library to the latest version.
- Verify image processing logic for transparency handling.
- Test affected image formats thoroughly.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-12491 vulnerability anywhere in the article.