vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator

Vulnerability Description

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.

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54
• https://github.com/vllm-project/vllm/pull/12366
• https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec0513d04
• https://pytorch.org/docs/stable/generated/torch.load.html