CVE-2025-24357
HIGHCVSS Vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Lifecycle Timeline
3Tags
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.
Analysis
vLLM is a library for LLM inference and serving. Rated high severity (CVSS 7.5), this vulnerability is remotely exploitable, no authentication required. This Deserialization of Untrusted Data vulnerability could allow attackers to execute arbitrary code through malicious serialized objects.
Technical Context
This vulnerability is classified as Deserialization of Untrusted Data (CWE-502), which allows attackers to execute arbitrary code through malicious serialized objects. 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. Affected products include: Vllm.
Affected Products
Vllm.
Remediation
A vendor patch is available. Apply the latest security update as soon as possible. Avoid deserializing untrusted data. Use safe serialization formats (JSON). Implement integrity checks and type allowlists.
Priority Score
Vendor Status
Share
External POC / Exploit Code
Leaving vuln.today