cbcvebase.
CVE-2026-49468
published 2026-06-22

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…

PriorityP262critical9.8CVSS 3.1
AVNACLPRNUINSUCHIHAH
EPSS
0.59%
45.9th percentile
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

9 ranges
VendorProductVersion rangeFixed in
ansible-automation-platform-26lightspeed-chatbot-rhel9
ansible-automation-platform-27lightspeed-chatbot-rhel9
berriailitellm< 1.84.01.84.0
exploit-intelligence-tech-previewvulnerability-analysis-rhel9
litellmlitellm< 1.84.01.84.0
litellmlitellm>= 0 < 1.84.01.84.0
rhoaiodh-llama-stack-core-rhel9
rhoaiodh-mlflow-rhel9
rhoaiodh-trustyai-garak-lls-provider-dsp-rhel9

Detection & IOCsextracted from sources · hover to see the quote

  • Authentication bypass is triggered by a crafted HTTP Host header that causes the auth gate to evaluate a different route than the one FastAPI dispatched — monitor for anomalous or malformed Host header values in requests to LiteLLM proxy management routes
  • The vulnerable code path is in litellm/proxy/auth/auth_utils.py::get_request_route(), which derives the effective route from request.url.path — audit or instrument this function for route mismatch between auth evaluation and FastAPI dispatch
  • Unauthenticated access attempts to protected management routes on LiteLLM proxy (versions prior to 1.84.0) should be treated as exploitation attempts of this vulnerability
  • ·Vulnerability only affects LiteLLM proxy versions prior to 1.84.0; upgrade to 1.84.0 or later to remediate
  • ·Red Hat products confirmed affected include: Red Hat OpenShift AI (RHOAI) packages (odh-llama-stack-core-rhel9, odh-mlflow-rhel9, odh-trustyai-garak-lls-provider-dsp-rhel9) and Red Hat Ansible Automation Platform 2 packages (lightspeed-chatbot-rhel9 for AAP 2.6 and 2.7)
  • ·If deployed behind a load balancer or API gateway, those components must be configured to strictly validate and sanitize the HTTP Host header before forwarding requests to prevent exploitation

CVSS provenance

nvdv3.19.8CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
nvdv4.09.5CRITICALCVSS: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:X
vendor_redhat9.8CRITICAL
Stop checking back — get the weekly exploitation signal.

Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.