CVE-2026-27893

Severity CVSS v4.0:

Pending analysis

Type:

CWE-693 Protection Mechanism Failure

Publication date:

27/03/2026

Last modified:

27/03/2026

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&#39;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.

Impact

Vector 3.x

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H CVSS v3.1 Severity and Metrics:

Base Score: 8.80 HIGH
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack Vector (AV): Network
Attack Complexity (AC): Low
Privileges Required (PR): None
User Interaction (UI): Required
Scope (S): Unchanged
Confidentiality (C): High
Integrity (I): High
Availability (A): High

Base Score 3.x

8.80

Severity 3.x

HIGH

CVE-2026-27893

Description

Impact

References to Advisories, Solutions, and Tools