DeutschShown in its original language — a full translation is planned for a future version.
vllm: Schwachstelle ermöglicht Codeausführung
view advisory published 2026-06-14
Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um beliebigen Programmcode auszuführen.
01
describes (1)
Related CVEs.
| ID | severity | exploitable | ||
|---|---|---|---|---|
| CVE-2026-41523US | — | — | ||
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthent… | ||||
02
references
External citations — patches, advisories, analysis.
- Red Hat Security Advisory RHSA-2026:36006 vom 2026-07-06external
- Red Hat Security Advisory RHSA-2026:57389 vom 2026-08-20external
- Red Hat Security Advisory RHSA-2026:59138 vom 2026-08-24external
- Red Hat Security Advisory RHSA-2026:59139 vom 2026-08-24external
- Red Hat Security Advisory RHSA-2026:61627 vom 2026-08-31external
- Red Hat Security Advisory RHSA-2026:61629 vom 2026-08-31external
- Red Hat Security Advisory RHSA-2026:62336 vom 2026-09-02external
- Red Hat Security Advisory RHSA-2026:70965 vom 2026-09-23external
scry
Advisories like this name the exposed products attackers go after on your perimeter. See what is exposed on your perimeter with a free passive scan.
Free scan