8.8High

CVE-2026-27893vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

vllm-project vllm; Red Hat Red Hat AI Inference Server 3.2; Red Hat Red Hat AI Inference Server 3.3; Red Hat Red Hat Enterprise Linux AI 3.3 Published: (7 months ago)

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.

Weakness (CWE): CWE-693CWE-501

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
ai inference server 3.2 —
ai inference server 3.3 —
enterprise linux ai 3.3 —
openshift ai 2.25 —
openshift ai 3.3 —
Red Hat Red Hat AI Inference Server all versions
Red Hat Red Hat AI Inference Server 3.2 all versions
Red Hat Red Hat AI Inference Server 3.3 all versions
Red Hat Red Hat Enterprise Linux AI 3.3 all versions
Red Hat Red Hat OpenShift AI 2.25 all versions
Red Hat Red Hat OpenShift AI 3.3 all versions
Red Hat Red Hat OpenShift AI (RHOAI) —
vllm-project vllm >= 0.10.1, < 0.18.0

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.10.1 < 0.18.0