- 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.
- Source
- security-advisories@github.com
- NVD status
- Analyzed
- Products
- vllm
CVSS 3.1
- Type
- Primary
- Base score
- 8.8
- Impact score
- 5.9
- Exploitability score
- 2.8
- Vector string
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Severity
- HIGH
- security-advisories@github.com
- CWE-502
- Hype score
- Not currently trending
[
{
"nodes": [
{
"negate": false,
"cpeMatch": [
{
"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"vulnerable": true,
"matchCriteriaId": "78210BFE-5D31-4D84-BA73-75C1594A3A3C",
"versionEndExcluding": "0.7.0"
}
],
"operator": "OR"
}
]
}
]