CVE-2026-27893

High

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.

SeverityHigh

CVSS8.8

Exploit probability—

ProductVllm

PublishedMar 27, 2026

First seenMar 27, 2026

Weakness typeCWE-693CWE-693

How to fix

Update

vllm vllm0.18.0 or later
vllm0.18.0 or later

Vendor advisories

Affected products

Product	Affected versions	Fixed in
vllm vllm	0.10.1 ≤ v < 0.18.0	0.18.0
vllmPyPI	0.10.1 ≤ v < 0.18.0	0.18.0

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.