cbcvebase.
CVE-2026-27893
published 2026-03-27

CVE-2026-27893: 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…

PriorityP359high8.8CVSS 3.1
AVNACLPRNUIRSUCHIHAH
EPSS
1.36%
68.3th percentile
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

3 ranges
VendorProductVersion rangeFixed in
vllm-projectvllm
vllmvllm>= 0.10.1 < 0.18.00.18.0
vllmvllm>= 0.10.1 < 0.18.00.18.0

CVSS provenance

nvdv3.18.8HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
ghsa8.8HIGH
osv8.8HIGH
vendor_redhat8.8HIGH
Stop checking back — get the weekly exploitation signal.

Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.