vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.
This vulnerability carries a HIGH severity rating with a CVSS v3.1 score of 7.5, indicating it can be exploited remotely over the network but requires specific conditions to be met though user interaction is required and does not require pre-existing privileges . The vulnerability impacts confidentiality (data exposure), integrity (unauthorized modifications), and availability (service disruption) for affected systems. Impacting 1 product from vllm organizations running these solutions should prioritize assessment and patching.
Reported in 2025, this vulnerability emerged during an era marked by increased sophistication in supply chain attacks, cloud infrastructure vulnerabilities, and software-as-a-service (SaaS) security challenges. Security practices during this period emphasized zero-trust architectures, container security, and API protection.
2025-01-27T18:15:41.523
2026-06-17T08:58:39.307
Analyzed
CVSSv3.1: 7.5 (HIGH)
SecUtils normalizes and enriches National Vulnerability Database (NVD) records by standardizing vendor and product identifiers, aggregating vulnerability metadata from both NVD and MITRE sources, and providing structured context for security teams. For vllm's affected products, we extract Common Platform Enumeration (CPE) data, Common Weakness Enumeration (CWE) classifications, CVSS severity metrics, and reference data to enable rapid vulnerability prioritization and asset correlation. This record contains no exploit code, proof-of-concept instructions, or attack methodologies—only defensive intelligence necessary for patch management, risk assessment, and security operations.