Red Hat Openshift Ai vulnerabilities

9 CVEs affecting Red Hat Openshift Ai, 2 known to be exploited (CISA KEV), with EPSS scores. Latest: CVE-2026-15154, published 2026-07-08.

Highest priority

Known exploited (CISA KEV) first, then by EPSS exploit probability.

CVE-2026-42271: BerriAI LiteLLM Command Injection Vulnerability, published 2026-05-08. High severity, CVSS 8.8. Actively exploited: in CISA KEV since 2026-06-08. EPSS: 92.6% chance of exploitation in the next 30 days. 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 endpoints used to preview an MCP server before saving it — POST…
CVE-2026-48710: Kludex Starlette HTTP Request/Response Smuggling Vulnerability, published 2026-05-26. Medium severity, CVSS 6.5. Actively exploited: in CISA KEV since 2026-09-02. EPSS: 7.1% chance of exploitation in the next 30 days. Starlette is a lightweight ASGI framework/toolkit. Prior to version 1.0.1, the HTTP `Host` request header was not validated before being used to reconstruct `request.url`. Because the routing…
CVE-2026-46625, published 2026-06-10. High severity, CVSS 7.5. EPSS: 1% chance of exploitation in the next 30 days. JavaScript Cookie is a JavaScript API for handling cookies, client-side. Prior to version 3.0.7, js-cookie's internal assign() helper copies properties with for...in + plain assignment. When the…
CVE-2024-7557, published 2024-08-12. High severity, CVSS 8.8. EPSS: 0.9% chance of exploitation in the next 30 days. A vulnerability was found in OpenShift AI that allows for authentication bypass and privilege escalation across models within the same namespace. When deploying AI models, the UI provides the option…
CVE-2023-54365, published 2026-06-23. High severity, CVSS 7.5. EPSS: 0.8% chance of exploitation in the next 30 days. 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 standard library's HTTP/2 implementation (CVE-2023-44487 /…
CVE-2026-5483, published 2026-04-10. Critical severity, CVSS 9.9. EPSS: 0.7% chance of exploitation in the next 30 days. A flaw was found in odh-dashboard in Red Hat Openshift AI. This vulnerability in the `odh-dashboard` component of Red Hat OpenShift AI (RHOAI) allows for the disclosure of Kubernetes Service Account…
CVE-2026-15154, published 2026-07-08. Medium severity, CVSS 6.5. EPSS: 0.5% chance of exploitation in the next 30 days. A flaw was found in `guardrails-detectors`, a component of Red Hat OpenShift AI. This vulnerability, known as Regular Expression Denial of Service (ReDoS), allows a remote attacker to provide…
CVE-2026-1462, published 2026-04-13. High severity, CVSS 7.8. EPSS: 0.4% chance of exploitation in the next 30 days. A vulnerability in the `TFSMLayer` class of the `keras` package, version 3.13.0, allows attacker-controlled TensorFlow SavedModels to be loaded during deserialization of `.keras` models, even when…
CVE-2025-12805, published 2026-03-26. High severity, CVSS 8.1. EPSS: 0.4% chance of exploitation in the next 30 days. 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,…