Skip to content
fr Sign in
7.1 High

CVE-2026-25960 vLLM is an inference and serving engine for large language models (LLMs)

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 products and versions

Product Affected versions Fixed in
Red Hat OpenShift AI 2.25 1783998857 earliest → < 1783998857 1783998857
Red Hat AI Inference Server Versions not published
Red Hat Enterprise Linux AI (RHEL AI) 3 Versions not published
Red Hat OpenShift AI (RHOAI) Versions not published
vllm 0.15 0.15.1 → < 0.17.0 0.17.0

References

Timeline

  1. Published
  2. Last modified

Other CVEs of Red Hat OpenShift AI 2.25

The 140 CVEs of Red Hat OpenShift AI 2.25 →
CVE-2026-86332 A flaw was found in odh-dashboard in Red Hat OpenShift AI 6.5 Medium CVE-2026-18620 A flaw was found in Data Science Pipelines 7.1 High CVE-2026-18618 A flaw was found in ml-metadata 7.5 High CVE-2026-18611 A flaw was found in the Data Science Pipelines Operator 7.5 High
Track this CVE