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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-502"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/24xxx/CVE-2025-24357.json"
}{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"extracted_events": [
{
"introduced": "0"
},
{
"fixed": "0.7.0"
}
],
"source": [
"CPE_RANGE",
"REFERENCES"
]
}