CVE-2026-49468
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/auth_utils.py::get_request_route(), which Starlette reconstructs from the Host header. A crafted Host could therefore make the auth gate evaluate a different route from the one FastAPI dispatched. This vulnerability is fixed in 1.84.0.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceLiteLLM proxy has a Host-header parsing flaw where the authentication layer derives the effective route from request.url.path in get_request_route(). Since Starlette reconstructs this path from the Host header, an attacker can craft a malicious Host header to make the auth gate evaluate a different route than FastAPI dispatched, achieving unauthenticated access to protected management routes.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 1.84.0CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Check installed LiteLLM versionRun `pip show litellm` or check the running proxy's /health endpoint for version info. If using Docker, check the image tag or run `docker images` to see the versioned image used.Affected if The installed version is earlier than 1.84.0 (e.g., 1.83.0, 1.82.0, etc.)
-
Verify LiteLLM proxy authentication configurationInspect the proxy's configuration file (config.yaml) or environment variables. Look for `LITELLM_MASTER_KEY`, `LITELLM_UI_USERNAME`/`PASSWORD`, or other auth-related settings defined in the deployment.Affected if Authentication is configured on the proxy (auth is required to detect the bypass; the flaw allows unauthenticated access to routes that should require it)
-
Determine network exposure of the proxyReview network configuration to see if the LiteLLM proxy is directly accessible from untrusted networks (e.g., internet-facing, behind a load balancer without host validation). Check if the proxy listens on 0.0.0.0 or a public IP.Affected if The proxy is accessible from untrusted networks where an attacker can control the Host header (not behind a reverse proxy that normalizes or restricts Host headers)
-
Inspect proxy access logs for anomalous Host headersReview the LiteLLM proxy access logs or reverse proxy logs for requests with unusual Host header values (e.g., internal endpoints, admin paths, or mismatched hostnames). Look for patterns like `Host: localhost`, `Host: 127.0.0.1`, or host values that differ from the expected proxy hostname.Affected if Logs show requests with manipulated Host headers targeting management or admin routes that should require authentication
You are affected if LiteLLM version is earlier than 1.84.0 AND the proxy is exposed to untrusted networks allowing arbitrary Host header injection, enabling potential unauthorized access to protected routes.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped1.84.0
Upgrade LiteLLM to version 1.84.0 or later to patch the Host header parsing vulnerability. Until upgrade is possible, consider placing a WAF in front that validates and normalizes Host headers.
1.84.0
- 1. Identify current LiteLLM version by checking the installed package or running `litellm --version`
- 2. Upgrade LiteLLM to version 1.84.0 or later using pip: `pip install litellm>=1.84.0`
- 3. Verify the upgrade was successful by checking the installed version: `pip show litellm`
- 4. Restart the LiteLLM proxy service to load the updated version
- 5. Test that management routes are properly protected and the fix is functioning
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation3.0 h
- Implementation4.0 h
- Testing6.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,128.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-49468 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-49468 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data