IP-DB.com
Türkçe English Deutsch Español
Anmelden API-Schlüssel holen
6.5Mittel

CVE-2026-34756vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server

vllm-project vllm; Red Hat Red Hat AI Inference Server 3.2; Red Hat Red Hat AI Inference Server 3.4; Red Hat Red Hat Enterprise Linux AI 3.4 Veröffentlicht: (vor 7 Monaten)

Beschreibung

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.

Schwachstellentyp (CWE): CWE-770CWE-1284

Daten: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Wiedergegeben wie in der Quelle, auf Englisch.

Betroffene Produkte und Versionen

HerstellerProduktVersionen
ai inference server 3.2 —
ai inference server 3.4 —
enterprise linux ai 3.4 —
Red Hat Red Hat AI Inference Server all versions
Red Hat Red Hat AI Inference Server 3.2 all versions
Red Hat Red Hat AI Inference Server 3.4 all versions
Red Hat Red Hat Enterprise Linux AI 3.4 all versions
Red Hat Red Hat OpenShift AI (RHOAI) all versions
vllm-project vllm >= 0.1.0, < 0.19.0

Referenzen und Patches

CPE-Treffer (NVD) (1)
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* ≥ 0.1.0 < 0.19.0

Neue CVEs im selben Produkt — Red Hat Enterprise Linux

7.3Hoch
CVE-2026-91151

Cockpit: cockpit: local privilege escalation via insecure symlink handling in public key addition helper

Red Hat Red Hat Enterprise Linux 10; Red Hat Red Hat Enterprise Linux 7; Red Hat Red Hat Enterprise Linux 8; Red Hat Red Hat Enterprise Linux 9

A flaw was found in Cockpit. A local authenticated user with control over a target account's home directory can exploit a privileged symlink dereference vulnerability in the `ssh-add-public-key.sh` helper. When this helper runs with elevated privileges, it ca…

7.8Hoch
CVE-2026-108472

Xfsprogs: xfsprogs: local privilege escalation via command injection in xfs_admin

Red Hat Red Hat Enterprise Linux 10; Red Hat Red Hat Enterprise Linux 7; Red Hat Red Hat Enterprise Linux 8; Red Hat Red Hat Enterprise Linux 9

A flaw was found in the xfs_admin utility in xfsprogs. The tool does not properly validate user-supplied parameters, allowing operating system command injection. A local attacker can exploit this issue by providing crafted input arguments, which may result in…

7.5Hoch
CVE-2026-91150

Cockpit: cockpit: denial of service via unbounded fragmented websocket messages

Red Hat Red Hat Enterprise Linux 10; Red Hat Red Hat Enterprise Linux 7; Red Hat Red Hat Enterprise Linux 8; Red Hat Red Hat Enterprise Linux 9

A flaw was found in Cockpit. This vulnerability allows a remote attacker, without prior authentication, to send specially crafted fragmented WebSocket messages. These messages accumulate without a total-size limit, leading to unbounded memory exhaustion and a…