Vulnerability in Berriai Litellm
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/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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
EPSS exploit prediction
EPSS 0.030, 87.7th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Berriai Litellm — versions < 1.84.0
- Litellm
Weakness classification (CWE)
Public exploits and proof-of-concept code
2 public repositories with exploit or proof-of-concept code for this CVE:
- BiiTts/CVE-2026-49468-LiteLLM-Auth-Bypass (5 stars, last pushed 2026-07-03): CVE-2026-49468 — LiteLLM (<1.84.0) unauthenticated auth bypass via Host-header route confusion. PoC + docker lab.
- krevetkqqq/CVE-2026-49468 (last pushed 2026-10-30)
References
- https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3w (Patch, Mitigation, Vendor Advisory)
- https://github.com/BerriAI/litellm/releases/tag/v1.84.0 (Product, Release Notes)
- access.redhat.com/security/cve/CVE-2026-49468
- bugzilla.redhat.com/show_bug.cgi
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-49468.json
This CVE has public exploit evidence. See the latest CVEs with public exploits.