CVEvulnerability

CVE-2026-27893

8.8 HIGH Published 2026-03-27 Modified 2026-07-21 Official page ↗
Status
Modified
Published
2026-03-27
Last modified
2026-07-21
Assigner
[email protected]
CVSS 3.1 ([email protected])
8.8 HIGH — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CVSS 3.1 (0b0ca135-0b70-47e7-9f44-1890c2a1c46c)
8.8 HIGH — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weaknesses
CWE-501, CWE-693

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.

Affected configurations

• vllm vllm (>= 0.10.1 < 0.18.0)

Related

Weakness · CWE (2)

  • CWE-501 Trust Boundary Violation weakness
  • CWE-693 Protection Mechanism Failure weakness

References