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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | < 0.7.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/d3d6bb13fb62da3234addf6574922a4ec051Patch
- https://github.com/vllm-project/vllm/pull/12366Issue TrackingPatch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rh4j-5rhw-hr54Vendor Advisory
- https://pytorch.org/docs/stable/generated/torch.load.htmlTechnical Description
FAQ
What is CVE-2025-24357?
CVE-2025-24357 is a vulnerability with a CVSS score of 7.5 (HIGH). 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 th...
How severe is CVE-2025-24357?
CVE-2025-24357 has been rated HIGH with a CVSS base score of 7.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-24357?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.