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.
Metrics
Affected Vendors & Products
References
History
Wed, 17 Jun 2026 12:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| References |
| |
| Metrics |
threat_severity
|
threat_severity
|
Wed, 17 Jun 2026 11:15:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations | |
| First Time appeared |
Redhat
Redhat ai Inference Server Redhat enterprise Linux Ai Redhat openshift Ai |
|
| Weaknesses | CWE-115 | |
| CPEs | cpe:/a:redhat:ai_inference_server:3 cpe:/a:redhat:enterprise_linux_ai:3 cpe:/a:redhat:openshift_ai |
|
| Vendors & Products |
Redhat
Redhat ai Inference Server Redhat enterprise Linux Ai Redhat openshift Ai |
|
| References |
| |
| Metrics |
cvssV3_1
|
Status: PUBLISHED
Assigner: redhat
Published:
Updated: 2026-06-17T14:47:57.047Z
Reserved: 2026-06-17T07:24:01.437Z
Link: CVE-2026-12491
No data.
No data.
OpenCVE Enrichment
No data.