CVE-2026-48746 is a critical-severity (CVSS 9.1) CWE-444 vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.
vLLM: OpenAI auth bypass
Exploitation Status
Proof-of-concept exploit code exists
- CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
- CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
Exploitation and automatability from CISA’s SSVC triage for CVE-2026-48746.
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
How urgent is this, really
CVE-2026-48746 plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.
Where this sits among everything scored
Of 379,145 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.
Real-World Exposure
vllmReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.
Description
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.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | ≥ 0.3.0&&< 0.22.0 | 0.22.0pip install --upgrade 'vllm==0.22.0' |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update vllm to 0.22.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-48746 is resolved across your whole dependency graph.
Workarounds
Put an independent control in front of the weakness: restrict the affected endpoint or interface to trusted networks, require an additional authentication factor or proxy-level check, and invalidate existing sessions and credentials in case the flaw has already been used.
How O3 protects you
O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like CVE-2026-48746 can be triaged on real exposure rather than presence alone.
Tailored to CVE-2026-48746. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Fixing This On Your OS
If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.
CVE-2026-48746 is an authentication bypass in the vLLM OpenAI-compatible API server. A remote attacker who can reach the vLLM endpoint directly can craft a Host header so the authentication middleware checks a different URL path than the one actually dispatched, bypassing VLLM_API_KEY / --api-key protection.…
Restrict network access to the vLLM API endpoint to only trusted clients and internal networks. Implement firewall rules or network policies to limit inbound connections to the vLLM service, thereby reducing the attack surface. This operational control helps prevent unauthorized external access to the vulnerable API.Source: Red Hat security advisory for CVE-2026-48746 (CC BY 4.0)
| Product | Fixed in | Advisory |
|---|---|---|
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-cuda-rhel9:1782951012 | RHSA-2026:36005 |
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-rocm-rhel9:1782951244 | RHSA-2026:36006 |
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-cuda-rhel9:1787860580 | RHSA-2026:61627 |
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-rocm-rhel9:1787884873 | RHSA-2026:61629 |
| Red Hat AI Inference Server 3.3 | rhaiis/vllm-rocm-rhel9:1782353093 | RHSA-2026:30088 |
| Red Hat AI Inference Server 3.3 | rhaiis/vllm-cuda-rhel9:1782352847 | RHSA-2026:30089 |
| Red Hat AI Inference Server 3.4 | rhaii/vllm-spyre-rhel9:1789681201 | RHSA-2026:69464 |
| Red Hat AI Inference Server 3.4 | rhaii/vllm-cpu-rhel9:1789681128 | RHSA-2026:69466 |
Frequently Asked Questions
Is CVE-2026-48746 in your dependencies?
O3 Security finds CVE-2026-48746 across PyPI dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.