vLLM Image Metadata Handling CVE: EXIF/TPNG tRNS Vulnerability
CVE-2026-12491 Published on June 17, 2026
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.
Vulnerability Analysis
CVE-2026-12491 can be exploited with network access, and does not require authorization privileges or user interaction. This vulnerability is consided to have a high level of attack complexity. The potential impact of an exploit of this vulnerability is considered to have no impact on confidentiality, with no impact on integrity and availability.
Timeline
Reported to Red Hat.
Made public.
Weakness Type
Misinterpretation of Input
The software misinterprets an input, whether from an attacker or another product, in a security-relevant fashion.
Products Associated with CVE-2026-12491
Want to know whenever a new CVE is published for Red Hat products? stack.watch will email you.