Deserialization in Vllm
CVE-2025-24357
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.
Vulnerability class: Insecure Deserialization
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.009, 60.0th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions < 0.7.0
Weakness classification (CWE)
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54 (Vendor Advisory)
- https://github.com/vllm-project/vllm/pull/12366 (Patch, Issue Tracking)
- https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04 (Patch)
- https://pytorch.org/docs/stable/generated/torch.load.html (Technical Description)