Redhat Openshift Ai vulnerabilities

CVE-2026-42271 [HIGH] CWE-77 CVE-2026-42271: LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1 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 /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and

CVE-2026-48710 [MEDIUM] CWE-444 CVE-2026-48710: Starlette is a lightweight ASGI framework/toolkit. Prior to version 1.0.1, the HTTP `Host` request h 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 algorithm relies on the raw HTTP path while `request.url` is rebuilt from the `Host` header, a malformed header could make `request.url.path` differ from the p

CVE-2026-5483 [CRITICAL] CWE-201 CVE-2026-5483: A flaw was found in odh-dashboard in Red Hat Openshift AI. This vulnerability in the `odh-dashboard` 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 tokens through a NodeJS endpoint. This could enable an attacker to gain unauthorized access to Kubernetes resources.

CVE-2025-12805 [HIGH] CWE-653 CVE-2025-12805: A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows una 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

CVE-2026-1462 [HIGH] CWE-502 CVE-2026-1462: A vulnerability in the `TFSMLayer` class of the `keras` package, version 3.13.0, allows attacker-con 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 `safe_mode=True`. This bypasses the security guarantees of `safe_mode` and enables arbitrary attacker-controlled code execution during model inference under t