CVE-2026-13717 PUBLISHED

Rhoai maas: llm-d: maas/llm-d inference gateway: default allowedroutes.namespaces.from: all allows namespace users to hijack shared model-serving traffic (tokens, prompts, outputs)

Assigner: redhat
Reserved: 29.06.2026 Published: 10.08.2026 Updated: 10.08.2026

A flaw was found in the Red Hat OpenShift AI (RHOAI) MaaS Gateway. Improper configuration of the Gateway in a model-serving context allows a standard user with low privileges to intercept, read, log, and alter all MaaS model traffic. This includes sensitive information such as access keys, input prompts, and outputs, leading to significant information disclosure and data tampering.

Metrics

CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CVSS Score: 8.8

Product Status

Vendor Red Hat
Product Red Hat OpenShift AI (RHOAI)
Versions Default: affected
Vendor Red Hat
Product Red Hat OpenShift AI (RHOAI)
Versions Default: affected
Vendor Red Hat
Product Red Hat OpenShift AI (RHOAI)
Versions Default: affected
Vendor Red Hat
Product Red Hat OpenShift AI (RHOAI)
Versions Default: affected
Vendor Red Hat
Product Red Hat OpenShift AI (RHOAI)
Versions Default: affected
Vendor Red Hat
Product Red Hat OpenShift AI (RHOAI)
Versions Default: affected

Workarounds

You can restrict Gateway access to some namespaces only. However, it does not prevent someone from an authorized namespace to hijack the traffic of another. Fully locking down access to the MaaS Gateway is a solution, however it defeats the self-service approach of the component.

References

Problem Types

  • Improper Access Control CWE