Browse / AI Framework and Platform Flaws / CVE-2026-115917
vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Information exposure
- Affected
- vllm (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:N/A:N
- EPSS
- 0.2% chance of exploitation in 30 days
How it works, in short
The server defaults to a wildcard CORS origin and has no auth unless an API key is set, so any web page can read responses from a reachable instance. (Our summary, written by a model. The source text is below.)
Details
Summary
The OpenAI-compatible server registers Starlette CORSMiddleware withallowed_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 examplelocalhost or an internal/VPN address) and read the responses. The defaultallow_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-CORSMiddleware- registration.
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), issue -
POST /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.
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
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0
Source: GitHub Advisory Database, used under CC BY 4.0.