CVE-2026-115917: vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server
Summary The OpenAI-compatible server registers Starlette CORSMiddleware with allowedorigins defaulting to [""], and performs no authentication unless --api-key (or VLLMAPIKEY) is configured. A web page on any origin can send requests to a vLLM server that the victim's browser can reach (for example localhost or an internal/VPN address) and read the responses.
Published Oct 28, 2026
Affected packages
vllm
- Ecosystem
- PyPI
- Affected
- < 0.32.0
- Fixed in
- 0.32.0
- Check
pip show vllm
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
Summary
The OpenAI-compatible server registers Starlette CORSMiddleware with allowed_origins defaulting to ["*"], and performs no authentication unless --api-key (or VLLM_API_KEY) is configured. A web page on any origin can send requests to a vLLM server that the victim's browser can reach (for example localhost or an internal/VPN address) and read the responses. The default allow_credentials=False blocks cookie-bearing cross-origin requests; because vLLM authenticates with a bearer header rather than cookies, the wildcard still permits untokenized access to an unauthenticated server and read access when the caller already holds a token.
Details
Affected components
vllm/entrypoints/launchers/cli_args.py-allowed_originsdefault value.vllm/entrypoints/serve/middleware/register.py-CORSMiddlewareregistration.vllm/entrypoints/serve/middleware/authenticate.py- auth middleware and its guarded path prefixes.
Root cause
vllm/entrypoints/launchers/cli_args.py:
allow_credentials: bool = False
"""Allow credentials."""
allowed_origins: list[str] = field(default_factory=lambda: ["*"])
"""Allowed origins."""vllm/entrypoints/serve/middleware/register.py:
app.add_middleware(
CORSMiddleware,
allow_origins=args.allowed_origins,
allow_credentials=args.allow_credentials,
allow_methods=args.allowed_methods,
allow_headers=args.allowed_headers,
)The auth middleware is added only when a token is configured and guards only the /v1, /v2, /inference, and /cohere prefixes. /v1/load_lora_adapter and /v1/unload_lora_adapter are inside /v1 and therefore do require a key when one is set; they are open only when no key is configured and dynamic LoRA updating is enabled.
Impact
- A malicious page can enumerate models (
GET /v1/models), issuePOST /v1/chat/completions, consume GPU time, and read model output through the victim's browser. - When the server is reachable only from the victim's network, the browser acts as a proxy a remote website could not otherwise use.
- With
allow_credentials=False, cookie-based CSRF does not apply; the exposure is cross-origin request execution and response disclosure.
This advisory was fixed in MR61009.
Credited to prnjlksingh, jperezdealgaba.
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmh
- https://nvd.nist.gov/vuln/detail/CVE-2026-115917
- https://github.com/vllm-project/vllm/pull/61009
- https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0
- https://github.com/advisories/GHSA-vvpg-rrww-wpmh
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
Coverage on the Beam blog
More vLLM vulnerabilities
All vLLM entriesCVE-2026-115911
vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
medium6.5Oct 28, 2026CVE-2026-115912
vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
high7.5Oct 28, 2026CVE-2026-115913
vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
medium6.5Oct 28, 2026CVE-2026-115914
vLLM DeepSeek-OCR image processing vulnerable to denial of service
medium6.5Oct 28, 2026CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
high8.1Oct 28, 2026CVE-2026-115916
vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
medium6.5Oct 28, 2026
