CVE-2026-49468
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/authutils.py::getrequest_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.
Package Versions Affected
Automatically patch vulnerabilities without upgrading
CVSS Version



Related Resources
References
https://github.com/BerriAI/litellm/releases/tag/v1.84.0, https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-49468.json, https://access.redhat.com/security/cve/CVE-2026-49468, https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3w, https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/49xxx/CVE-2026-49468.json, https://nvd.nist.gov/vuln/detail/CVE-2026-49468, https://bugzilla.redhat.com/show_bug.cgi?id=2491520