← Back to CVEs

CVE-2026-25960

HIGH

7.1

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.

CVE Details

CVSS v3.1 Score7.1

SeverityHIGH

CVSS VectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L

Attack VectorNETWORK

ComplexityLOW

Privileges RequiredLOW

User InteractionNONE

Published3/9/2026

Last Modified3/18/2026

Sourcenvd

Honeypot Sightings0

Affected Products

vllm:vllm

Weaknesses (CWE)

CWE-918

References

https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0(security-advisories@github.com)

https://github.com/vllm-project/vllm/pull/34743(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc(security-advisories@github.com)

https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536(security-advisories@github.com)

IOC Correlations

No correlations recorded

This product uses data from the NVD API but is not endorsed or certified by the NVD.