CVE-2025-24357
Last modified
CVE-2025-24357 is a high-severity vulnerability rated 8.8/10 on the CVSS scale. 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. EPSS estimates a 0.69% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | < 0.7.0 |
References
- https://github.com/vllm-project/vllm/pull/12366Issue Tracking, Patch
- https://pytorch.org/docs/stable/generated/torch.load.htmlTechnical Description
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-24357?
How severe is CVE-2025-24357?
How do I fix CVE-2025-24357?
Are you affected by CVE-2025-24357?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
