CVEvulnerability

CVE-2026-25960

9.8 CRITICAL Published 2026-03-09 Modified 2026-07-21 Official page ↗
Status
Modified
Published
2026-03-09
Last modified
2026-07-21
Assigner
[email protected]
CVSS 3.1 ([email protected])
7.1 HIGH — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L
CVSS 3.1 ([email protected])
9.8 CRITICAL — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS 3.1 (0b0ca135-0b70-47e7-9f44-1890c2a1c46c)
7.1 HIGH — CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L
Weaknesses
CWE-474, CWE-918

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.

Affected configurations

• vllm vllm (>= 0.15.1 < 0.17.0)

Related

Weakness · CWE (2)

  • CWE-474 Use of Function with Inconsistent Implementations weakness
  • CWE-918 Server-Side Request Forgery weakness

References