CVE Feed

    Dashboard / CVE / CVE-2026-12491

    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
    Redhat
    Product
    Ai Inference Server
    Vendor
    Redhat
    Product
    Enterprise Linux Ai
    Vendor
    Redhat
    Product
    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