CVE-2026-115917Vllm · Vllm
Vulnerability data via NVD (ingested)
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.
External references
Search for exposed instances
Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).
vuln:CVE-2026-115917product:"Vllm Vllm"http.html:"Vllm"More intel sources (5)
vuln:CVE-2026-115917vulnerabilities.cve_id: CVE-2026-115917CVE-2026-115917CVE-2026-115917"CVE-2026-115917" exploit -site:nvd.nist.gov