DeutschShown in its original language — a full translation is planned for a future version.
vllm: Schwachstelle ermöglicht Codeausführung
view advisory published 2026-03-26
Ein entfernter, anonymer Angreifer kann eine Schwachstelle in vllm ausnutzen, um beliebigen Programmcode auszuführen.
01
describes (1)
Related CVEs.
| ID | severity | exploitable | ||
|---|---|---|---|---|
| CVE-2026-27893US | — | — | ||
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_rem… | ||||
02
references
External citations — patches, advisories, analysis.
- Red Hat Security Advisory RHSA-2026:10140 vom 2026-04-23external
- Red Hat Security Advisory RHSA-2026:10141 vom 2026-04-23external
- Red Hat Security Advisory RHSA-2026:19712 vom 2026-05-21external
- Red Hat Security Advisory RHSA-2026:19724 vom 2026-05-21external
- Red Hat Security Advisory RHSA-2026:24977 vom 2026-06-10external
- Red Hat Security Advisory RHSA-2026:37275 vom 2026-07-09external
- vLLM GitHub vom 2026-03-26external
- WID-SEC-W-2026-0890 - CSAF Versionself
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