CVE-2026-27893
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.
Fraqueza
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.
Produtos afetados
- vllm vllm
Referências
- https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
- https://github.com/vllm-project/vllm/pull/36192
- https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
- https://access.redhat.com/errata/RHSA-2026:10140
- https://access.redhat.com/errata/RHSA-2026:10141
- https://access.redhat.com/errata/RHSA-2026:19712
Encontre a falha antes de um atacante.
Entre com o GitHub e rode sua primeira auditoria em menos de um minuto. O plano gratuito não exige cartão de crédito.