---
title: "CVE-2026-49468: LiteLLM: Authentication Bypass via Host Header Injection"
url: https://erroneo.us/security/cve/CVE-2026-49468/
description: "CVE-2026-49468 (litellm (PyPI)): LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, a Host-header…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-06-22
date_modified: 2026-07-18
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-49468"
kev: false
cvss: 9.5
epss: 0.03033
license: All rights reserved. Quote with attribution and a link.
---

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

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 3.0% , percentile 87: FIRST’s model estimates a 3.0% chance of exploitation activity in the next 30 days, higher than 87% of all scored CVEs (elevated). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes litellm (PyPI) < 1.84.0, fixed in 1.84.0 . Check your lockfile, including transitive dependencies.

## What it is

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::getrequestroute(), 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 packages

- PyPI `litellm` < 1.84.0 → fixed: 1.84.0

## Affected products (CVE record)

- BerriAI litellm: < 1.84.0

## Severity

- GitHub_M CVSS 4.0: 9.5 `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`
- redhat-SADP CVSS 3.1: 8.1 `CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H`
- GitHub CVSS 4.0: 9.5 `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`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 3.03% probability of exploitation activity in the next 30 days; percentile 87.

## Sources

- [GitHub Advisory GHSA-4xpc-pv4p-pm3w](https://github.com/advisories/GHSA-4xpc-pv4p-pm3w)
- [CVE.org record CVE-2026-49468](https://www.cve.org/CVERecord?id=CVE-2026-49468)
- [NVD entry CVE-2026-49468](https://nvd.nist.gov/vuln/detail/CVE-2026-49468)
- [github.com](https://github.com/BerriAI/litellm/security/advisories/GHSA-4xpc-pv4p-pm3w)
- [github.com](https://github.com/BerriAI/litellm/releases/tag/v1.84.0)
- [access.redhat.com](https://access.redhat.com/security/cve/CVE-2026-49468)
- [RHBZ#2491520](https://bugzilla.redhat.com/show_bug.cgi?id=2491520)
- [security.access.redhat.com](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-49468.json)
- [github.com](https://github.com/BerriAI/litellm)
- [github.com](https://github.com/pypa/advisory-database/tree/main/vulns/litellm/PYSEC-2026-388.yaml)
- [pypi.org](https://pypi.org/project/litellm)

---
Source page: https://erroneo.us/security/cve/CVE-2026-49468/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt