EUVD-2026-31493

The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trustremotecode=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.frompretrained to import and execute arbitrary Python files included in any model pulled fr...

Ludwig framework is vulnerable to insecure deserialization in its model serving component

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...

EUVD-2026-29151

OpenClaw before 2026.4.23 contains an improper access control vulnerability in the gateway tool's config.apply and config.patch operations that allows compromised models to write unsafe configuration changes by bypassing an incomplete denylist protection. Attackers can persist malicious config...

CosyVoice 安全漏洞

CosyVoice is an open-source voice generation and AI voice cloning platform developed by FunAudioLLM. CosyVoice has a security vulnerability, which stems from the gRPC server component using torch.load to load the voice synthesis model without enabling the weights-only=True security parameter. Thi...

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

...

UBUNTU-CVE-2026-34445

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...

CVE-2026-34445 ONNX: Malicious ONNX models can crash servers by exploiting unprotected object settings.

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...

CVE-2026-34445

CVE-2026-34445 affects ONNX prior to version 1.21.0, where ExternalDataInfo used Python setattr() to load metadata directly from model files without validating keys, enabling a malicious model to overwrite internal object properties. Impact is mainly availability (HIGH) with confidentiality and i...

Deserialization of Untrusted Data

Overview nemo-toolkit is a NeMo - a toolkit for Conversational AI Affected versions of this package are vulnerable to Deserialization of Untrusted Data through the torch.load checkpoint and model import paths in the nemo collections and checkpoint utilities. An attacker can execute arbitrary code...

Resources Downloaded over Insecure Protocol

Overview onnx is an Open Neural Network Exchange Affected versions of this package are vulnerable to Resources Downloaded over Insecure Protocol via the onnx.hub.load function when the silent parameter is set to True. An attacker can bypass repository trust verification and suppress all security...

PT-2026-22151

Name of the Vulnerable Software and Affected Versions Flair versions 0.4.1 through latest Description The deserialization of untrusted data in the LanguageModel class can lead to arbitrary code execution when loading a malicious model. Recommendations Versions prior to 0.4.1 are not affected. At...

CVE-2025-33212

Summary: NVIDIA NeMo Framework’s model-loading vulnerability could enable code execution, privilege escalation, DoS, or data tampering when loading a malicious file. Root cause: improper control during file/model loading. Impact: HIGH across confidentiality, integrity, and availability. Exploitat...

Remote Code Execution (RCE)

Rasa is vulnerable to Remote Code Execution RCE. The vulnerability is due to improper handling of maliciously crafted models in Rasa, which allows an attacker to load a model remotely into a Rasa instance if certain security configurations are not in place...

PYSEC-2024-82

Deserialization of untrusted data can occur in versions 23.3.2.0 and newer of the MindsDB platform, enabling a maliciously uploaded model to run arbitrary code on the server when interacted with...

MindsDB 安全漏洞

MindsDB is an emerging low-code machine learning platform from MindsDB, Inc. A security vulnerability exists in MindsDB version 23.10.2.0 and earlier, which stems from the presence of deserialization of untrusted data, allowing maliciously uploaded models to run arbitrary code on the server when...