CVE-2026-27893

[CVE catalog]

Severity

High · CVSS 8.8CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Published

Mar 26, 2026, 11:00:00 PM UTC

Source

[NVD] · [CVE record]

EPSS

1.37% · Oct 25, 2026

A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). Two model implementation files hardcode `trust_remote_code=True` when loading sub-components. This bypasses the user's explicit `--trust-remote-code=False` security opt-out, allowing a remote attacker to achieve remote code execution through malicious model repositories. vllm: vLLM: Remote code execution due to hardcoded trust_remote_code setting This is an Important vulnerability in vLLM, as shipped in Red Hat AI Inference Server and Red Hat OpenShift AI. The flaw allows remote code execution due to vLLM hardcoding `trust_remote_code=True` when loading sub-components, which bypasses the user's explicit `--trust-remote-code=False` security opt-out. This can lead to exploitation through malicious model repositories. The CVSS score(s) listed for this vulnerability do not reflect the associated product's status, and are included for informational purposes to better understand the severity of this vulnerability.