Vulnerability record · CVE-2026-27893 · published 27 March 2026
CVE-2026-27893: Vllm vulnerability
Vllm · Vllm
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.
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:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Affected products
1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.
References
Track CVE-2026-27893 inside VULONE
Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.
Related vulnerabilities
Same products first, then exploited flaws of the same weakness class.
Source: NIST National Vulnerability Database (record CVE-2026-27893), CISA KEV, FIRST EPSS (scores of 2026-09-26). This page is refreshed as NVD updates the record.
