Attestkeep
Langue : Français
S'inscrire

Vulnérabilités / CVE-2026-25960

critique

CVE-2026-25960

vLLM: vLLM: Server-Side Request Forgery bypass via inconsistent URL parsing

Publiée Modifiée CWE 918, 474
Dans la Trivy database depuis au moins le 24 oct. 2026, 07:11 UTCLa date d'entrée avant ce build n'est pas enregistrée.

Sévérité par source

NVD9.8CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GHSA5.4CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
Red Hat7.1CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L

Le label propre à Trivy est CRITICAL. Critique selon NVD. Plus basse selon Red Hat (élevée), GHSA (moyenne).

Description

vLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the load_from_url_async method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. The SSRF fix uses urllib3.util.parse_url() to validate and extract the hostname from user-provided URLs. However, load_from_url_async uses aiohttp for making the actual HTTP requests, and aiohttp internally uses the yarl library for URL parsing. This vulnerability in 0.17.0.

Paquets affectés et versions corrigées

SourcePaquetCorrigé en
pip::GitHub Security Advisory pipvllm0.17.0

Références

Les 15 références

Vulnerability data compiled from the Trivy vulnerability database (trivy-db, Aqua Security, Apache License 2.0), which aggregates third-party advisories. CVE records are published by The MITRE Corporation under the CVE Terms of Use; CVE is a trademark of MITRE. This product uses data from the NVD API but is not endorsed or certified by the NVD. Severity, titles and advisory data from the GitHub Advisory Database (CC BY 4.0), Red Hat security data (CC BY 4.0) and the other sources linked on each entry. Entries may be summarised or re-formatted; the linked original is the authoritative record.