The vulnerability in odh-model-controller (CVE-2026-16456) arises from improper validation in the loadSecret function, which reads the Secret namespace based on user-controlled input. An authenticated user with custom resource creation permissions can exploit this to access sensitive information such as API keys and cloud credentials from namespaces they should not have access to, resulting in information disclosure. The CVSS v3.1 base score is 6.5 (medium severity), reflecting network attack vector, low attack complexity, and privileges required. Red Hat has published advisories and updated container images for Red Hat OpenShift AI to mitigate this issue.

An attacker with authenticated access and permissions to create custom resources can read sensitive secrets from other namespaces, potentially exposing API keys and cloud credentials. This leads to information disclosure but does not affect integrity or availability. There are no reports of active exploitation in the wild.

Red Hat has released updated container images for Red Hat OpenShift AI that address this vulnerability. Users should upgrade to the fixed versions as per Red Hat's official guidance and documentation. Patch status is confirmed by Red Hat advisories. Follow the upgrade instructions at https://docs.redhat.com/en/documentation/red_hat_openshift_ai/ to fully apply the errata updates. No additional mitigations are specified by the vendor.