CVE 8.8 HIGH

vLLM’s hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out_CVE-2026-27893

8.8 / 10
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

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.

Basic Information

ID CVE-2026-27893
Source GitHub_M
Published Mar 26, 2026 at 23:56
Modified Mar 27, 2026 at 13:52

Affected Product

Vendor vllm-project
Product vllm
Version >= 0.10.1, < 0.18.0
Affected Versions vllm-project vllm >= 0.10.1, < 0.18.0

CWE Classification

References

💭 Join the Security Discussion

🔒 Your email address will not be published. Required fields are marked *

⚠️ Please be respectful and constructive in your comments. Security discussions should remain professional.