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.
The vulnerability concerns the authentication mechanism in the LiteLLM proxy server (AI Gateway), which is used to forward requests to various language model (LLM) API interfaces. According to CWE-290 classification, an attacker can bypass identity verification through spoofing — impersonating a trusted entity. The attack vector is network-based (AV:N), requires no user interaction or privileges (PR:N, UI:N), and the impacts include high impact on confidentiality, integrity, and availability of both the main component and related systems.
An unauthenticated remote attacker can gain unauthorized access to the LiteLLM proxy server, which may lead to takeover of configuration, leakage of data transmitted to AI models, and disruption of service availability, as well as potential impact on related systems (SC:H, SI:H, SA:H).
LiteLLM must be updated immediately to version 1.84.0 or later. The patch is available in the official GitHub repository at: https://github.com/BerriAI/litellm/releases/tag/v1.84.0
LiteLLM (BerriAI) in all versions before 1.84.0
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XLitellm
APPLitellm< 1.84.0
Related vulnerabilities
SQL Injection w LiteLLM umożliwia nieautoryzowany dostęp do bazy danych
Atak supply chain na Trivy — złośliwe tagi GitHub Actions i obraz kontenera
LiteLLM: pominięcie uwierzytelnienia JWT przez kolizję klucza cache (Auth Bypass)
RCE w BerriAI/litellm poprzez endpoint /config/update
BerriAI LiteLLM – SSTI via Jinja umożliwia RCE przez endpoint /completions