Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD 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.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
NONE
Momentum
NONE
⚠️ HIGH — CVE-2026-115917 vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server config… CVSS 3.4 ⚡ Exploit in the wild Full analysis → https://sec.kaitan.id/cves/CVE-2026-115917 #OpenAI #CyberSecurity #InfoSec