Vulnerability in Vllm-Project Vllm

CVE-2026-12491

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.

Published · last modified .

CVSS v3 metric

CVSS v3 base score 4.8 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L.

EPSS exploit prediction

EPSS: 0.002 (15.1th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 15th percentile — 15.1% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2026-12491: held from 0.002 to 0.002.

EPSS over last 30 days · oldest: 0.002 · newest: 0.002 · change: 0.000

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-12491?
CVE-2026-12491 is a medium-severity vulnerability in Vllm-Project Vllm, classified under CWE-115. CVSS score: 4.8/10. Published 2026-06-17.
How severe is CVE-2026-12491?
Medium severity. CVSS v3 base score is 4.8 out of 10.