VDB

CVE-2026-25960

CVE-2026-25960 PUBLISHED CVSS 7.099999904632568 HIGH

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.

EPSS 0.03% · 8.3th percentile

Risk Scores

CVSS 3.1
7.099999904632568
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L
EPSS Score
0.03%
8.3th percentile

Affected Products

VendorProductVersions
vllm-projectvllm>= 0.15.1, < 0.17.0, >= 0.15.1, < 0.17.0, *
PyPIvllm0.15.1, 0.15.1, 0.15.1
vllmvllm0.15.1, 0.15.1, 0.15.1

Timeline

  • Mar 9, 2026 CVE Published
  • Mar 9, 2026 PoC Published
  • Mar 10, 2026 CVE Updated
  • Mar 10, 2026 EPSS Score
  • Mar 11, 2026 EPSS Score
  • Mar 12, 2026 EPSS Score
  • Mar 13, 2026 EPSS Score
  • Mar 14, 2026 EPSS Score
  • Mar 15, 2026 EPSS Score
  • Mar 16, 2026 EPSS Score
  • Mar 17, 2026 EPSS Score
  • Mar 17, 2026 Security Advisory
Open in Interactive Console →
$ Console Community · 100/wk Open console ›