LiteLLM 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.
Weakness
This attack-focused weakness is caused by incorrectly implemented authentication schemes that are subject to spoofing attacks.
Affected Software
| Name | Vendor | Start Version | End Version |
|---|---|---|---|
| Litellm | Litellm | * | 1.84.0 (excluding) |
Related Attack Patterns
- https://cwe.mitre.org/data/definitions/21.html
- https://cwe.mitre.org/data/definitions/22.html
- https://cwe.mitre.org/data/definitions/459.html
- https://cwe.mitre.org/data/definitions/461.html
- https://cwe.mitre.org/data/definitions/473.html
- https://cwe.mitre.org/data/definitions/476.html
- https://cwe.mitre.org/data/definitions/59.html
- https://cwe.mitre.org/data/definitions/60.html
- https://cwe.mitre.org/data/definitions/667.html
- https://cwe.mitre.org/data/definitions/94.html
References
- https://github.com/BerriAI/litellm/releases/tag/v1.84.0
- https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3w
- https://access.redhat.com/security/cve/CVE-2026-49468
- https://bugzilla.redhat.com/show_bug.cgi?id=2491520
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-49468.json