CVE-2026-27893

HIGH

8.8

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.

CVE Details

CVSS v3.1 Score8.8

SeverityHIGH

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

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredNONE

User InteractionREQUIRED

Published3/27/2026

Last Modified3/30/2026

Sourcenvd

Honeypot Sightings0

Affected Products

vllm:vllm

Weaknesses (CWE)

CWE-693

References

https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72(security-advisories@github.com)

https://github.com/vllm-project/vllm/pull/36192(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.