SOURCE-LINKED INTELLIGENCE

GHSA-rh4j-5rhw-hr54: vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator

OSV AI package advisories · observation · Jan 27, 2025 · UTC

### Description The vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It use torch.load function and weights_only parameter is default value False. There is a security warning on https://pytorch.org/docs/stable/generated/torch.load.html, when torch.load load a malicious pickle data it will execute arbitrary code during unpickling. ### Impact This vulnerability can be exploited to execute arbitrary codes and OS commands in the victim machine who fetch the pretrained repo remotely. Note that most models no

Read original source ↗ Open in workspace

recordType

vulnerability

status

active

evidenceStatus

reported

region

Global