SecBoard
Zurück zur CVE-Übersicht

CVE-2026-27893

HIGH(8.8)

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Risk Signal Score22/100 — NIEDRIG
  • CVSS 8.8 — Hoch

EPSS-Score

1%

Exploit-Wahrscheinlichkeit (30 Tage)

CVSS Score

8.8

Technische Schwere

Beschreibung

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.

Referenzen