Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
CRITICAL severity

CVE-2026-48746 — vllm

CRITICALFix: vllm-project/vllm#43426

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

Also known asGHSA-94f4-hr76-p5j6PYSEC-2026-226
Published
Jun 22, 2026
Updated
Sep 18, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Sep 26, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

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

via FIRST.org ↗
1.2%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs66th percentile — riskier than 66% of all scored CVEsHighest risk

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

1 pkg affected
🐍vllm

Real-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

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm≥ 0.3.0&&< 0.22.00.22.0pip install --upgrade 'vllm==0.22.0'

Detection & mitigation playbook

Open-source dependency
  1. Detect

    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.

  2. 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.

  3. 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.

  4. 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.

Red HatImportant

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.…

Workaround published by Red Hat
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)
ProductFixed inAdvisory
Red Hat AI Inference Server 3.2rhaiis/vllm-cuda-rhel9:1782951012RHSA-2026:36005
Red Hat AI Inference Server 3.2rhaiis/vllm-rocm-rhel9:1782951244RHSA-2026:36006
Red Hat AI Inference Server 3.2rhaiis/vllm-cuda-rhel9:1787860580RHSA-2026:61627
Red Hat AI Inference Server 3.2rhaiis/vllm-rocm-rhel9:1787884873RHSA-2026:61629
Red Hat AI Inference Server 3.3rhaiis/vllm-rocm-rhel9:1782353093RHSA-2026:30088
Red Hat AI Inference Server 3.3rhaiis/vllm-cuda-rhel9:1782352847RHSA-2026:30089
Red Hat AI Inference Server 3.4rhaii/vllm-spyre-rhel9:1789681201RHSA-2026:69464
Red Hat AI Inference Server 3.4rhaii/vllm-cpu-rhel9:1789681128RHSA-2026:69466

Frequently Asked Questions

### 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`. ```py from starlette.datastructures import URL, Headers, Mu
O3 Security · Impact-Aware SCA

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.

CVE-2026-48746: vllm (Critical 9.1) | O3 Security