CVE-2025-24357
vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator
- State
- Published
- Severity
- 7.5 High
- Published
- Jan 27, 2025
- Updated
- Feb 12, 2025
- Reserved
- Jan 20, 2025
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 7.5 High | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H | GitHub_M |
Weaknesses
- CWE-502 Deserialization of Untrusted Data
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.