LiteLLM: Authentication Bypass via Host Header Injection
48Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 9.5epss 0.6%
from disclosure to weapon11 days
Published on NVDJun 22
1st PoC+11d
exploitation probability
0.6%top 55% of all CVEs
observed exploitation
nono source reports it
1 public exploit(s)
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.
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
Affected products
BerriAI · litellmpublic PoCs found — 1
githubgithub.com/BiiTts/CVE-2026-49468-LiteLLM-Auth-Bypass★ 0⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.
References
https://access.redhat.com/security/cve/CVE-2026-49468https://bugzilla.redhat.com/show_bug.cgi?id=2491520https://github.com/BerriAI/litellm/releases/tag/v1.84.0https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3whttps://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-49468.json