CVE-2026-25960

Severity CVSS v4.0:

Pending analysis

Type:

CWE-918 Server-Side Request Forgery (SSRF)

Publication date:

09/03/2026

Last modified:

09/03/2026

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.

Impact

Vector 3.x

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L CVSS v3.1 Severity and Metrics:

Base Score: 7.10 HIGH
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L

Attack Vector (AV): Network
Attack Complexity (AC): Low
Privileges Required (PR): Low
User Interaction (UI): None
Scope (S): Unchanged
Confidentiality (C): High
Integrity (I): None
Availability (A): Low

Base Score 3.x

7.10

Severity 3.x

HIGH

CVE-2026-25960

Description

Impact

References to Advisories, Solutions, and Tools