CVE-2025-24357
vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator
Using vllm by vllm-project?
Get instant alerts when new vulnerabilities affect vllm - before attackers find them.
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.
Remediation
No guide yetNo remediation guidance has been written for this CVE yet. What the record does show:
References (4)
SSVC — Action Prioritization
SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.
CVSS
- Attack Vector
- NETWORK
- Complexity
- LOW
- Privileges
- NONE
- User Interaction
- REQUIRED
- Scope
- UNCHANGED
- Confidentiality
- HIGH
- Integrity
- HIGH
- Availability
- HIGH
Quick Info
Get alerted
Stop reading CVE feeds looking for your own stack
Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.