CVE-2026-27893

HIGH EPSS 50.3%
Published Mar 27, 20263mo ago · Modified Jun 17, 20261w ago
8.8 CVSS 3.1
High
Find Similar
Published Mar 27, 2026 3mo ago
Last Modified Jun 17, 2026 1w ago

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.

CVSS Details

Base Score
8.8
Exploitability
2.8
Impact
5.9
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction Required
Scope Unchanged
Confidentiality High
Integrity High
Availability High

Threat Intelligence

EPSS Exploit Probability
50.3% percentile
Exploit & Patch Status
No Known Exploit
Patch Available

Weaknesses 1

CWE-693

Affected Products 1

VendorProductVersionRange
vllmvllm*≥0.10.1  –  <0.18.0

References 3

  • github.com https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
    Patch
  • github.com https://github.com/vllm-project/vllm/pull/36192
    Issue Tracking
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59
    Vendor Advisory

Remediation

  • github.com https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72
    Patch