CVE-2026-12491
Published: Wed, 17 Jun 2026 13:20
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 transpare
Details
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.
Are YOU affected by CVE-2026-12491?
5-second check on your actual server. Reads /etc/os-release, uname -r, and dpkg-query; matches against the live USN + Debian Security Tracker feeds; tells you whether CVE-2026-12491 (and any other live CVE) applies. Anonymous, no signup.
curl https://mindsparkstack.com/scan.sh | bash
References
StackPatch runs this match against YOUR installed packages every hour
Free (3 servers) / from $9/mo (14-day free trial) / Solo $9/mo / Pro $29/mo / Team $79/mo. Indie pricing.