GHSA-8JR5-V98P-W75M vLLM: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations

Summary Issue 1: EXIF orientation not normalized → The image orientation processed by the model differs from how humans view it, introducing interpretation bias. Issue 2: PNG tRNS not explicitly flattened before converting to RGB → After conversion, transparent/semi-transparent pixels are rendere...

CVE-2026-12491

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 informatio...

CVE-2026-12491 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 informatio...

CVE-2026-12491 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 informatio...

CVE-2026-12491

CVE-2026-12491 affects the vLLM library used for LLM inference. The issue stems from improper handling of image metadata during image processing, specifically EXIF orientation and PNG transparency (tRNS). When converting images to RGB, transparency information may be discarded or remapped, causin...

CVE-2026-12491

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 informatio...