RHSA-2026:30056HighCVSS 9.1

Red Hat Security Advisory: RHOAI 3.3.4 - Red Hat OpenShift AI

Published
June 25, 2026
Last Modified
October 9, 2026

🔗 CVE IDs covered (4)

CVE-2026-35029 →CVE-2026-35030 →CVE-2026-40217 →CVE-2026-42271 →

📋 Description

CVE-2026-35029 — litellm: LiteLLM: Remote code execution and privilege escalation via unrestricted proxy configuration endpoint CVE-2026-35030 — litellm: LiteLLM: Authentication bypass and privilege escalation via OIDC userinfo cache key collision CVE-2026-40217 — LiteLLM: LiteLLM: Arbitrary Code Execution via bytecode rewriting CVE-2026-42271 — litellm: LiteLLM: Authenticated command execution via MCP stdio test endpoints

🎯 Affected products8

  • Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-llama-stack-core-rhel9@sha256:b6ec1fac474c9ff596322446656add0ebb10c449d623c37a3f71548957dc4c9c_amd64 as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-llama-stack-core-rhel9@sha256:ee821288511aaf6e91080f8a925a425e5d26eeacc73f042b39469c65c2e7a139_arm64 as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-operator-bundle@sha256:163f636a1cbc151572ad0470bd5b06650980efd72e6c462cff6ce9ce4bcfaa93_amd64 as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-rhel9-operator@sha256:195a25181e1ff5c73cea1146a339489398cb54618e8cd9d574e90a72a1ff3e11_arm64 as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-rhel9-operator@sha256:48a73c9e0491f2f9bb109e15fea89ebd65939ed9bcfced506e006f23bbe9f64e_ppc64le as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-rhel9-operator@sha256:5b0afdcb5c35d4c55847e1eb2967056ef9f508549f40028d6a6d2b41f6e70fe6_amd64 as a component of Red Hat OpenShift AI 3.3
  • registry.redhat.io/rhoai/odh-rhel9-operator@sha256:f7788f465a7f7d03b8ac7b1de0994e99eb95693f78120856420e7d2426a3c466_s390x as a component of Red Hat OpenShift AI 3.3

✅ Remediation

For Red Hat OpenShift AI 3.3.4 see the following documentation, which will be updated shortly for this release, for important instructions on how to upgrade your cluster and fully apply this errata update: https://docs.redhat.com/en/documentation/red_hat_openshift_ai/ Workaround: Limit network access to the LiteLLM service to trusted networks or hosts only. Implement firewall rules to restrict inbound connections to the LiteLLM service's port, ensuring that only authorized systems can reach the service. This reduces the exposure of the `/config/update` endpoint to unauthorized authenticated users. Workaround: To mitigate this issue, ensure that JWT authentication is not enabled in LiteLLM configurations. The vulnerability only manifests when `enable_jwt_auth` is set to `true`. If JWT authentication is not strictly required, disable it to prevent potential authentication bypass and privilege escalation. If this configuration is changed, a restart of the LiteLLM service may be required for the changes to take effect. Workaround: Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base or stability.

🔗 References (8)