Categories
CVE-2026-48746 critical CVSS 9.1

Vulnerability in vllm (CVE-2026-48746)

Summary

Vulnerability in vllm (CVE-2026-48746). Confidential information can be exposed externally. Exploitable via AuthenticationMiddleware. Mitigation: upgrade to 0.22.0 or later.

Original description

The description as published by the source.

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 routin…

Source: GitHub Security Advisories (Global) NVD GitHub Advisory

Auto-generated summary

Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.

A vulnerability tracked as CVE-2026-48746 has been found in vllm.
Attackers can target a specific entry point like AuthenticationMiddleware over the network to misuse the product.
Confidential information can be exposed externally. CVSS score: 9.1/10.
What to do: upgrade vllm to 0.22.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-48746" on the vendor's site.

CVE-2026-48746 (vllm) — CWE-444 / CVSS v3 9.1
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: AuthenticationMiddleware / VLLM_API_KEY / url_path / URL
Patched: 0.22.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.

❓ What is the problem

A vulnerability (CWE-444) exists in vllm. Attackers reach the vulnerable code path via AuthenticationMiddleware without authentication.

📍 Affected scope

Check the vendor advisory for the affected versions of vllm. Attack surface: AuthenticationMiddleware / VLLM_API_KEY / url_path / URL.

🔥 Severity

Severity: Critical (CVSS 9.1/10). Confidential information can be exposed externally.

🔧 How to fix

Update to 0.22.0.

🛡️ Workaround

Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.

🔍 Detection

Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'vllm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.

Response actions

Concrete steps and command examples for SOC/SRE teams to execute in order

  1. 1
    Identify exposure identify
    grep -r 'vllm' . | grep -v node_modules

    リポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で vllm を grep し、稼働しているサービス・バージョンを把握する。

  2. 2
    Apply patch patch
    Upgrade vllm to 0.22.0

    ステージング環境で 0.22.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。

  3. 3
    Post-deployment verification verify
    Confirm patched version is live in production

    パッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。

Affected packages

pip vllm
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.22.0"}]}]
PyPI vllm
[{"type":"ECOSYSTEM","events":[{"introduced":"0.3.0"},{"fixed":"0.22.0"}]}]

References

We use cookies for analytics and ad measurement. This setting applies to all Game co., Ltd. sites. Details