Bug 2342304 (CVE-2025-24357)

Summary: CVE-2025-24357 vllm: vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security DevOps Team <prodsec-dev>
Status: NEW --- QA Contact:
Severity: high Docs Contact:
Priority: high    
Version: unspecifiedCC: jeder
Target Milestone: ---Keywords: Security
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: If docs needed, set a value
Doc Text:
A flaw was found in the vLLM package, a library for LLM inference and serving. The vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint 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 can be exploited to execute arbitrary codes and OS commands in the victim machine that fetches the pre-trained repo remotely.
 Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2025-01-27 18:01:32 UTC 
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.