CVE-2026-12491
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.
Published:Jun 10, 2026
Last Modified:Jun 17, 2026
EPS:Jun 17, 2026
EPSS Score:0.00239
CVSS Score:4.8
Affected Products
Vendor
Product
Action
Vendor
Redhat
Product
Ai Inference Server
Redhat
Ai Inference Server
Vendor
Redhat
Product
Enterprise Linux Ai
Redhat
Enterprise Linux Ai
Vendor
Redhat
Product
Openshift Ai
Redhat
Openshift Ai
Exploits
No exploit reference
Common Weakness Enumeration
Common Attack Pattern Enumeration and Classification (CAPEC)
No CAPEC recorded yet
Related CVEs
Common Vulnerability Scoring System
Attack Vector
Network
Adjacent
Local
Physical
Privileges Required
None
Low
High
User Interaction
None
Required
Scope
Unchanged
Changed
Confidentiality
None
Low
High
Integrity
None
Low
High
Availability
None
Low
High
