cvedb.io
CVE-2025-24357
HIGH · CVSS 7.5
EPSS exploitation probability: 0%
Published 2025-01-27T18:15:41.523 · Last modified 2026-06-17T08:58:39.307

Summary

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.

Affected products

vllm — vllm

Does this affect you?

Add your gear to cvedb and we'll alert you only when vllm ships something exploited.

Check my exposure →

References

This product uses data from the NVD API but is not endorsed or certified by the NVD. Informational only; not professional security advice.