LLMMedium
CVE-2026-12491: A flaw was found in vLLM, an open-source library for large language model inference. This vulnerabil…
- Occurred
- Jun 17, 2026
- Published
- Jun 17, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-12491
- cvss:MEDIUM
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: CVE describes a vulnerability in vLLM image processing affecting LLM inference integrity.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8