Description
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user-s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.
CVSS 8.8EPSS 1.346%Risque 0.99
Voir la source- Publication
- 2026-03-27 00:16:22
- Versions concernées
- >=0.10.1,<0.18.0
- Type
- Core software
- Dernière modification
- 2026-07-21 12:17:51
- Vecteur
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H