CVE-2026-12491
CVE-2026-12491 · Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
This page contains facts from public vulnerability sources. Check the original advisory before updating.
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.
CVSS 4.8 · Medium · EPSS 0.2% · Fix available
- Published
- Updated
Stack: python
Affected products and versions
vllm
- Versions
- ≥ 0.11.0, < 0.24.0: Affected (semver)
Update to 0.24.0
red hat ai inference server
No fix published
red hat enterprise linux ai (rhel ai) 3
No fix published
red hat openshift ai (rhoai)
No fix published
vllm PyPI
- Versions
- 0.11.0
- 0.11.1
- 0.11.2
- 0.12.0
- 0.13.0
- 0.14.0
- 0.14.1
- 0.15.0
- 0.15.1
- 0.16.0
- 0.17.0
- 0.17.1
- 0.18.0
- 0.18.1
- 0.19.0
- 0.19.1
- 0.20.0
- 0.20.1
- 0.20.2
- 0.21.0
- 0.22.0
- 0.22.1
- 0.23.0
- Affected ranges
- ECOSYSTEM: ≥ 0.11.0, < 0.24.0
Update to 0.24.0
vllm PyPI
- Versions
- 0.11.0
- 0.11.1
- 0.11.2
- 0.12.0
- 0.13.0
- 0.14.0
- 0.14.1
- 0.15.0
- 0.15.1
- 0.16.0
- 0.17.0
- 0.17.1
- 0.18.0
- 0.18.1
- 0.19.0
- 0.19.1
- 0.20.0
- 0.20.1
- 0.20.2
- 0.21.0
- 0.22.0
- 0.22.1
- 0.23.0
- Affected ranges
- ECOSYSTEM: ≥ 0.11.0, ≤ 0.23.0
No fix published