4.8
Medium
CVE-2026-12491 A flaw was found in vLLM, an open-source library for large language model inference
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 and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| Red Hat AI Inference Server | Versions not published | |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Versions not published | |
| Red Hat OpenShift AI (RHOAI) | Versions not published | |
| vllm 0.11 | 0.11.0 → < 0.24.0 | 0.24.0 |
References
- access.redhat.com access.redhat.com
- RHBZ#2489786 bugzilla.redhat.com
Timeline
- Published
- Last modified
Other CVEs of Red Hat AI Inference Server
The 65 CVEs of Red Hat AI Inference Server →
CVE-2026-114406
Ca-certificates: distrust emudhra intermediate ca certificates due to security concerns
6.8
Medium
CVE-2026-92925
Redis: redis: out-of-bounds read via crafted cluster bus packets
7.1
High
CVE-2026-18621
A flaw was found in Data Science Pipelines (DSP)
7.6
High
CVE-2026-58049
FFmpeg's RASC video decoder (decode_dlta in libavcodec/rasc.c) performs 32-bit reads and writes at the row cursor before…
8.6
High