CVSS 3.1
8.8 highCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HCVE-2025-24357
High (8.8) in vllm vllm. EPSS 0.9% chance of exploitation in the next 30 days. Fixed in vllm 0.7.0.
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.
Severity
- EPSS
- 0.9% chance of exploitation in the next 30 days; higher than 58% of CVEs (scores of 2026-10-31)
- CWE
- CWE-502
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-rh4j-5rhw-hr54 | PyPI | vllm | <0.7.0 | 0.7.0 |
| PYSEC-2025-58 | PyPI | vllm | <0.7.0 | 0.7.0 |