6.5

CVE-2026-73559

Exploit

vLLM: Completion prompt lists fan out into unbounded engine requests

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Vllm ≫ Vllm Version >= 0.19.0 < 0.26.0
VulnDex Vulnerability Enrichment
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Zu dieser CVE wurde keine Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.39% 0.319
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
security-advisories@github.com 6.5 2.8 3.6
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CWE-400 Uncontrolled Resource Consumption

The product does not properly control the allocation and maintenance of a limited resource.

https://github.com/vllm-project/vllm/releases/tag/v0.26.0
Release Notes
https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
Vendor Advisory
Exploit
https://github.com/vllm-project/vllm/pull/47845
Patch
Issue Tracking
https://github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
Patch