Redhat Openshift Ai — known CVE vulnerabilities

Every CVE whose affected-product data names Redhat Openshift Ai, ordered by CVSS severity, with EPSS exploit prediction and CISA KEV status.

CVEs (7)

• CVE-2026-42271 — CVSS 8.8 (high) — actively exploited: LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two…
• CVE-2024-7557 — CVSS 8.8 (high): A vulnerability was found in OpenShift AI that allows for authentication bypass and privilege escalation across models within the same…
• CVE-2026-5483 — CVSS 8.5 (high): A flaw was found in odh-dashboard in Red Hat Openshift AI. This vulnerability in the `odh-dashboard` component of Red Hat OpenShift AI…
• CVE-2025-12805 — CVSS 8.1 (high): A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack…
• CVE-2026-1462 — CVSS 7.8 (high): A vulnerability in the `TFSMLayer` class of the `keras` package, version 3.13.0, allows attacker-controlled TensorFlow SavedModels to be…
• CVE-2023-54365 — CVSS 7.5 (high): Traefik before 2.10.5 and 3.0.0-beta4 is affected by a denial-of-service vulnerability in HTTP/2 request handling inherited from the Go…
• CVE-2026-15154 — CVSS 6.5 (medium): A flaw was found in `guardrails-detectors`, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of…