CVEPublished 2026-03-27Modified 2026-06-301 article on news6 live referencesNVD data

CVE-2026-27893Vllm · Vllm

Vulnerability data via NVD (ingested)

CVSS v3.1
8.8
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS percentile
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.

Timeline
Published 2026-03-27
Modified 2026-06-30

External references

Search for exposed instances

Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).

More intel sources (5)

Known PoCs on GitHub

No public proof-of-concept repositories found for CVE-2026-27893 on GitHub.