9.5Critical

CVE-2026-49468LiteLLM: Authentication Bypass via Host Header Injection

BerriAI litellm; Red Hat Exploit Intelligence; Red Hat Red Hat Ansible Automation Platform 2; Red Hat Red Hat OpenShift AI (RHOAI) Published: (4 months ago)

Description

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 (CWE): CWE-290

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
BerriAI litellm < 1.84.0
litellm litellm < 1.84.0
Red Hat Exploit Intelligence all versions
Red Hat Red Hat Ansible Automation Platform 2 all versions
Red Hat Red Hat OpenShift AI (RHOAI) all versions

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* < 1.84.0