Количество 4
Количество 4
CVE-2025-12805
A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data.
CVE-2025-12805
A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data.
GHSA-cq3g-qvxc-ghr5
A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data.
BDU:2026-07529
Уязвимость платформы для разработки моделей искусственного интеллекта OpenShift AI, связанная с недостаточным пространственным разделением, позволяющая нарушителю оказать воздействие на конфиденциальность и целостность защищаемой информации
Уязвимостей на страницу
Уязвимость | CVSS | EPSS | Опубликовано | |
|---|---|---|---|---|
 | CVE-2025-12805 A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data. | CVSS3: 8.1 | 0% Низкий | 7 месяцев назад |
 | CVE-2025-12805 A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data. | CVSS3: 8.1 | 0% Низкий | 4 месяца назад |
| GHSA-cq3g-qvxc-ghr5 A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As a result, a user in one namespace can access another user’s Llama Stack instance and potentially view or manipulate sensitive data. | CVSS3: 8.1 | 0% Низкий | 4 месяца назад |
 | BDU:2026-07529 Уязвимость платформы для разработки моделей искусственного интеллекта OpenShift AI, связанная с недостаточным пространственным разделением, позволяющая нарушителю оказать воздействие на конфиденциальность и целостность защищаемой информации | CVSS3: 8.1 | 0% Низкий | 4 месяца назад |
Уязвимостей на страницу