← Übersicht Nicht im beobachteten Stack

ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.

CVE-2026-34445 · AZL-81989 · DEBIAN-CVE-2026-34445 · DHI-lel2-cs5y-6civ-df7i · GHSA-538c-55jv-c5g9 · PYSEC-2026-2240 · UBUNTU-CVE-2026-34445

Hoch · CVSS 8.6 Ubuntu: mediumRed Hat: Moderate Netzwerk · ohne Login Kein Fix bekannt

Veröffentlicht
01.04.2026
Zuletzt geändert
19.11.2026
EPSS (30 Tage)
0.3 %
CVSS-Vektor
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H

Beschreibung

Originaltext der Quelle, nicht übersetzt.

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to version 1.21.0, the ExternalDataInfo class in ONNX was using Python’s setattr() function to load metadata (like file paths or data lengths) directly from an ONNX model file. It didn’t check if the "keys" in the file were valid. Due to this, an attacker could craft a malicious model that overwrites internal object properties. This issue has been patched in version 1.21.0.

Status beim Hersteller

Red Hat stuft seine Produktlinien ein: 1 betroffen, 2 behoben, 2 nicht betroffen.

Red Hat OpenShift AI (RHOAI) BetroffenFix ausstehend rhoai/odh-openvino-model-server-rhel9
Red Hat OpenShift AI 2.25 Behoben rhoai/odh-pipeline-runtime-datascience-cpu-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-llmcompressor-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-rocm-py312-rhel9, rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-tensorflow-rocm-py312-rhel9, rhoai/odh-workbench-codeserver-datascience-cpu-py312-rhel9, rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-cuda-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-llmcompressor-cuda-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-rocm-py312-rhel9, rhoai/odh-workbench-jupyter-tensorflow-cuda-py312-rhel9, rhoai/odh-workbench-jupyter-tensorflow-rocm-py312-rhel9, rhoai/odh-workbench-jupyter-trustyai-cpu-py312-rhel9 RHSA-2026:65126
Red Hat OpenShift AI 3.3 Behoben rhoai/odh-pipeline-runtime-datascience-cpu-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-llmcompressor-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-pytorch-rocm-py312-rhel9, rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9, rhoai/odh-pipeline-runtime-tensorflow-rocm-py312-rhel9, rhoai/odh-workbench-codeserver-datascience-cpu-py312-rhel9, rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-cuda-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-llmcompressor-cuda-py312-rhel9, rhoai/odh-workbench-jupyter-pytorch-rocm-py312-rhel9, rhoai/odh-workbench-jupyter-tensorflow-cuda-py312-rhel9, rhoai/odh-workbench-jupyter-tensorflow-rocm-py312-rhel9, rhoai/odh-workbench-jupyter-trustyai-cpu-py312-rhel9 RHSA-2026:73987
Nicht betroffen (2)
Red Hat OpenShift AI 2.25Nicht betroffenverwundbarer Code nicht enthaltenrhoai/odh-built-in-detector-rhel9, rhoai/odh-caikit-nlp-rhel9, rhoai/odh-caikit-tgis-serving-rhel9, rhoai/odh-codeflare-operator-rhel9, rhoai/odh-dashboard-rhel9, rhoai/odh-data-science-pipelines-argo-argoexec-rhel9, rhoai/odh-data-science-pipelines-argo-workflowcontroller-rhel9, rhoai/odh-data-science-pipelines-operator-controller-rhel9, rhoai/odh-feast-operator-rhel9, rhoai/odh-feature-server-rhel9, rhoai/odh-fms-guardrails-orchestrator-rhel9, rhoai/odh-guardrails-detector-huggingface-runtime-rhel9, rhoai/odh-kf-notebook-controller-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-kserve-storage-initializer-rhel9, rhoai/odh-kuberay-operator-controller-rhel9, rhoai/odh-kueue-controller-rhel9, rhoai/odh-llama-stack-core-rhel9, rhoai/odh-llama-stack-k8s-operator-rhel9, rhoai/odh-llm-d-inference-scheduler-rhel9, rhoai/odh-llm-d-routing-sidecar-rhel9, rhoai/odh-ml-pipelines-api-server-v2-rhel9, rhoai/odh-ml-pipelines-driver-rhel9 und 38 weitere
Red Hat OpenShift AI 3.3Nicht betroffenverwundbarer Code nicht enthaltenrhoai/odh-built-in-detector-rhel9, rhoai/odh-cli-rhel9, rhoai/odh-dashboard-rhel9, rhoai/odh-data-science-pipelines-argo-argoexec-rhel9, rhoai/odh-data-science-pipelines-argo-workflowcontroller-rhel9, rhoai/odh-data-science-pipelines-operator-controller-rhel9, rhoai/odh-feast-operator-rhel9, rhoai/odh-feature-server-rhel9, rhoai/odh-fms-guardrails-orchestrator-rhel9, rhoai/odh-guardrails-detector-huggingface-runtime-rhel9, rhoai/odh-kf-notebook-controller-rhel9, rhoai/odh-kserve-agent-rhel9, rhoai/odh-kserve-controller-rhel9, rhoai/odh-kserve-router-rhel9, rhoai/odh-kserve-storage-initializer-rhel9, rhoai/odh-kube-auth-proxy-rhel9, rhoai/odh-kuberay-operator-controller-rhel9, rhoai/odh-llama-stack-core-rhel9, rhoai/odh-llama-stack-k8s-operator-rhel9, rhoai/odh-llm-d-inference-scheduler-rhel9, rhoai/odh-llm-d-routing-sidecar-rhel9, rhoai/odh-maas-api-rhel9, rhoai/odh-ml-pipelines-api-server-v2-rhel9, rhoai/odh-ml-pipelines-driver-rhel9, rhoai/odh-ml-pipelines-launcher-rhel9 und 44 weitere
Weitere betroffene Pakete (14)
Azure Linux:3pytorch2.2.2-14AZL-81989
CVEonnx/onnxkein Fix bekanntCVE-2026-34445
Debian:12onnxkein Fix bekanntDEBIAN-CVE-2026-34445
Debian:13onnxkein Fix bekanntDEBIAN-CVE-2026-34445
Debian:14onnxkein Fix bekanntDEBIAN-CVE-2026-34445
Docker Hardened Images:Debian:13onnxkein Fix bekanntDHI-lel2-cs5y-6civ-df7i
NVDlinuxfoundation:onnx1.21.0CVE-2026-34445
PyPIonnx1.21.0GHSA-538c-55jv-c5g9
PyPIonnx1.21.0PYSEC-2026-2240
Ubuntu:22.04:LTSonnxkein Fix bekanntUBUNTU-CVE-2026-34445
Ubuntu:25.10onnxkein Fix bekanntUBUNTU-CVE-2026-34445
Ubuntu:26.04:LTSonnxkein Fix bekanntUBUNTU-CVE-2026-34445
Ubuntu:26.10onnxkein Fix bekanntUBUNTU-CVE-2026-34445
Ubuntu:Pro:24.04:LTSonnxkein Fix bekanntUBUNTU-CVE-2026-34445

Empfohlene Prüfung

  1. Feststellen, ob und in welcher Version die betroffenen Pakete in Ihren Systemen, Images und Abhängigkeiten vorkommen.
  2. Wo eine Fix-Version genannt ist: aktualisieren. Wo nicht: Hersteller-Advisory und Referenzen auf Workarounds prüfen.
  3. Erreichbarkeit beachten: Der Angriffsweg (Netzwerk · ohne Login) ist aus dem CVSS-Vektor abgeleitet.

Diese Seite sagt nichts darüber, ob Ihre Systeme betroffen sind. Das klärt erst eine Prüfung Ihrer Versionen.