CVE-2026-12491— Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations

Vllm: vllm: image exif rotation & png trns transparency not normalized, causing mismatch between model input and expectations

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:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L

输入的错误解释

vLLM 输入验证错误漏洞

vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM存在输入验证错误漏洞，该漏洞源于对图片元数据（尤其是EXIF方向及PNG透明度数据）处理不当。图片转换为RGB过程中透明度信息被隐式丢弃或重映射，导致透明像素渲染异常和输入内容畸变，可能造成模型错误解读图片内容并影响处理数据的完整性。

N/A

N/A