CVE-2026-115917
MEDIUM
MEDIUM
Priority: 0.01
BB Relevance:
59/100
Published: 2026-10-26
Modified: 2026-10-28
First seen: 2026-10-29
Status: active
Attack Surface
Network
Low Complexity
No Auth
Scope Change
CVSS Vector Breakdown
AV:
Network
AC:
Low
PR:
None
UI:
Required
S:
Changed
C:
Low
I:
None
A:
None
Description
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.
Weakness Classification (1)
References & Advisories (4)
Release Notes
Patch
Vendor Advisory
Patch
Patch