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.
References2
Metrics
- CVSS 3.1
-
4.8
MEDIUM
Score source: CNA
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L - EPSS — exploit probability
- 0% percentile: 15 · as of 16 November 2026
- CWE
- CWE-115
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.