CVE-2026-25960

SSRF Protection Bypass in vLLM

State
Published
Severity
7.1 High
Published
Mar 9, 2026
Updated
Jul 21, 2026
Reserved
Feb 9, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
3.17.1 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:LGitHub_M
3.17.1 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:Lredhat-SADP

Weaknesses

  • CWE-918 Server-Side Request Forgery (SSRF)
  • CWE-474 Use of Function with Inconsistent Implementations

Affected Products

ProductVersions
vllmvllm-project
  • >= 0.15.1, < 0.17.0Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.