CVE-2026-49468

published 22 Jun 2026 · updated 15 Jul 2026

LiteLLM: Authentication Bypass via Host Header Injection

10.0CriticalCVSS 9.5EPSS 3%1 public exploits

A public exploit exists; no exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 3%. No fixed version is recorded.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
BerriAILiteLLM<1.84.0

Exploit evidence

1 public sources

Timeline

Every event on this vulnerability

Related

Other vulnerabilities in LiteLLM, strongest first

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-49468 severity on Zeptric[![CVE-2026-49468](https://zeptric.io/badge/cve/CVE-2026-49468.svg)](https://zeptric.io/cve/CVE-2026-49468)