GHSA-VVPG-RRWW-WPMH
vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server
Ciclo de vida de la vulnerabilidad
| Fecha | Fase | Evento | Detalle |
|---|---|---|---|
| Remediación | Parche 0.32.0 | vllm · -10 d desde divulgación | |
| Divulgación | Publicada | GHSA-VVPG-RRWW-WPMH divulgada | |
| Divulgación | Modificada | Última actualización del registro | |
| Monitoreo | Detectada | Ingresó al índice |
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_origins` default value.
- `vllm/entrypoints/serve/middleware/register.py` - `CORSMiddleware`
- `vllm/entrypoints/serve/middleware/authenticate.py` - auth middleware and its
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
- When the server is reachable only from the victim's network, the browser acts
- With `allow_credentials=False`, cookie-based CSRF does not apply; the exposure
This advisory was fixed in MR61009 https://github.com/vllm-project/vllm/pull/61009.
Rangos afectados
Estado del parche por paquete
| Paquete / producto | Estado | Corregida en | Desde divulgación | Última versión |
|---|---|---|---|---|
pypivllm |
Corregida | 0.32.0 | -10 d | 0.34.0 no afectada |
0.32.0Arsenal público
Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.
https://nvd.nist.gov/vuln/detail/CVE-2026-115917https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmhhttps://github.com/vllm-project/vllm/pull/61009https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aahttps://github.com/vllm-project/vllmhttps://github.com/vllm-project/vllm/releases/tag/v0.32.0Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.
