CVE-2026-12491 - Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations
CVE ID :CVE-2026-12491
Published : June 17, 2026, 10:07 a.m. | 1 hour, 31 minutes ago
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.
Severity: 4.8 | MEDIUM
Visit the link for more details, such as CVSS details, affected products, timeline, and more...
Published : June 17, 2026, 10:07 a.m. | 1 hour, 31 minutes ago
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.
Severity: 4.8 | MEDIUM
Visit the link for more details, such as CVSS details, affected products, timeline, and more...