CVE-2026-27893

8.8 HIGH
Published: March 27, 2026 Modified: March 30, 2026
View on NVD

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.

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

Login to generate AI explanation

CVSS v3.x Details

0.0 Low Medium High Critical 10.0
Vector String
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory
https://github.com/vllm-project/vllm/pull/36192
Source: security-advisories@github.com
Issue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
Source: security-advisories@github.com
Vendor Advisory

3 reference(s) from NVD

Quick Stats

CVSS v3 Score
8.8 / 10.0
EPSS (Exploit Probability)
0.0%
9th percentile
Exploitation Status
Not in CISA KEV

Weaknesses (CWE)

Affected Vendors

vllm