vLLM: OpenAI auth bypass
Published 16 Jun 2026 · Updated 10 Sept 2026
Is your project on an affected vllm?
Look after several Python apps? Indie watches up to 15 repos, private ones too, for $5 a month. See Indie
Affected package
- Affected
- >=0.3.0 <0.22.0
- Fixed in
- 0.22.0
pip install 'vllm>=0.22.0'Details
Summary
A vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware, which was discovered during @x41sec's source code audit.
It allows to use the API without providing the configured VLLM_API_KEY or --api-key.
Details
In https://github.com/vllm-project/vllm/blob/v0.14.0/vllm/entrypoints/openai/api_server.py#L689-L692 the url_path is taken from the URL, which is reconstructed by _starlette_ based on the request scope.
from starlette.datastructures import URL, Headers, MutableHeaders, State
# ...
url_path = URL(scope=scope).path.removeprefix(root_path)
headers = Headers(scope=scope)
if url_path.startswith("/v1") and not self.verify_token(headers):
response = JSONResponse(content={"error": "Unauthorized"}, status_code=401)
return response(scope, receive, send)
return self.app(scope, receive, send)The request scope includes the request's Host: header and reconstructs the URL as shown below:
f"{scheme}://{host_header}{path}"Neither starlette nor any of the ASGI servers (including uvicorn, which vllm uses) properly filter the Host: header for invalid characters. This allows an attacker to include special URL characters such as / or ? in the Host: header and thereby control the reconstructed URL and it's .path attribute.
FastAPI/starlette's routing uses the HTTP path and does not depend on the parsed url.path attribute, allowing attackers to reach an endpoint via a certain path while providing a different value in the .path.
Impact
- Instances of vllm that use an API Key for the OpenAI API and expose the API to attackers.
- Instances behind an RFC-conforming web server (such as nginx) are not affected.
Is GHSA-94f4-hr76-p5j6 in any of your client repos?
Checking one package by hand is fine. Checking it across forty client projects is not. NPMscan reads the lockfiles in every GitHub repo you pick, finds each project with an affected vllm, and gives you the command that fixes it.
More advisories for vllm
- LowCVE-2026-115917vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server · 28 Oct 2026
- MediumCVE-2026-115913vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine · 28 Oct 2026
- MediumCVE-2026-115914vLLM DeepSeek-OCR image processing vulnerable to denial of service · 28 Oct 2026
- HighCVE-2026-115915vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE · 28 Oct 2026
- HighCVE-2026-115912vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled · 28 Oct 2026
- MediumCVE-2026-115916vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS) · 28 Oct 2026
References
- Linkgithub.com/vllm-project/vllm/security/advisories/GHSA-94f4-hr76-p5j6
- Advisorynvd.nist.gov/vuln/detail/CVE-2026-48746
- Linkgithub.com/vllm-project/vllm/pull/43426
- Linkx41-dsec.de/lab/advisories/x41-2026-002-starlette
- Linksecurity.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-48746.json
- Packagegithub.com/vllm-project/vllm
- Linkgithub.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-226.yaml
- Linkbugzilla.redhat.com/show_bug.cgi?id=2491581
- Linkaccess.redhat.com/security/cve/CVE-2026-48746
- Linkaccess.redhat.com/errata/RHSA-2026:61629
- Linkaccess.redhat.com/errata/RHSA-2026:61627
- Linkaccess.redhat.com/errata/RHSA-2026:43038
- Linkaccess.redhat.com/errata/RHSA-2026:42644
- Linkaccess.redhat.com/errata/RHSA-2026:42142
- Linkaccess.redhat.com/errata/RHSA-2026:42132
- Linkaccess.redhat.com/errata/RHSA-2026:36006
- Linkaccess.redhat.com/errata/RHSA-2026:36005
- Linkaccess.redhat.com/errata/RHSA-2026:30089
- Linkaccess.redhat.com/errata/RHSA-2026:30088
Advisory data from OSV.dev (opens OSV.dev in a new tab), refreshed daily.