CVE-2026-12491
Medium · 4.8CVSS
4.8
EPSS
0.2%
Published
Jun 17, 2026
CISA due date
—
The record
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.
Affected packages
| Ecosystem | Package | Introduced | Fixed |
|---|
Related vulnerabilities
- CVE-2026-63650 OpenVPN 2.7_alpha1 through 2.7.5 using mbedTLS allows remote authenticated users to be… CWE-115
- CVE-2026-42004 An attacker can send a crafted EDNS OPT record that will be ignored by DNSdist’s… CWE-115
- CVE-2025-68113 ALTCHA is privacy-first software for captcha and bot protection. CWE-115
- GHSA-6gvq-jcmp-8959 ALTCHA Proof-of-Work Vulnerable to Challenge Splicing and Replay CWE-115
- CVE-2025-22870 Matching of hosts against proxy patterns can improperly treat an IPv6 zone ID as a… CWE-115