CVE-2026-49468

criticalpriority · attend · 50EPSS 0.030 · 87 %ileexploit · PoCDEEUUS
grimoire priorityP1 · Urgent
Exploitable?
Public exploit
1 exploit · PoC
Likely / severe?
3.03% (87th) EPSS
CVSS 9.8 · critical
Is it mine?
5 products
Check your exposure
Who says so?
5 sources
cnnvd · enisa_euvd · osv · cert_bund

EPSS · scored 2026-10-26

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.

01

cvss

Technical severity, 0–10. One row per scoring source.

9.8
010

base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · high–critical · 8.1–9.8

v3.19.8criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:Hprimary · NVD / NIST USexploitability 3.9 · impact 5.9
v3.18.1highCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:Hsecondaryexploitability 2.2 · impact 5.9
v3.19.8criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:Hsecondary · OSV
v4.09.5criticalCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:Hsecondary · ENISA EU
v4.09.5criticalCVSS: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:Xsecondary · security-advisories@github.com
v4.09criticalCVSS: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:P/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:Xsecondary · CVSS-BT (t0sche)
02

ssvc

A stakeholder decision — act, attend, or track — from exploitation and impact.

Exploitation: none · Automatable: yes · Technical Impact: totalcoordinatorcisa_ssvcUS
03

weaknesses

The CWE weakness classes this flaw belongs to.

CWE-290USCWE-290US
04

exploits (1)

Public proof-of-concept and weaponised exploit code.

05

affected products (5)

Products and version ranges known to be affected.

06

advisories (3)

Vendor and ecosystem advisories describing this.

  • WID-SEC-W-2026-1975LiteLLM: Schwachstelle ermöglicht Umgehen von SicherheitsvorkehrungenDeutsch2026-06-16csaf · cert_bundDE

    Ein entfernter, anonymer Angreifer kann eine Schwachstelle in LiteLLM ausnutzen, um Sicherheitsvorkehrungen zu umgehen.

  • GHSA-4xpc-pv4p-pm3wLiteLLM: Authentication Bypass via Host Header Injection2026-06-16ghsa · osvUS

    ### Impact 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. **Most deployments are not affected.** The bypass is blocked by any upstream layer that validates or normalizes `Host`, such as: - a CDN or WAF, such as Cloudflare - a reverse proxy with `server_name` allowlists - a host-based load balancer **LiteLLM Cloud customers are not affected.** ### Patches Fixed in **`1.84.0`**. Upgrade to `1.84.0` or later. No configuration change is required. ### Workarounds If upgrading is not immediately possible, place the proxy behind an upstream component that validates or normalizes the `Host` header before forwarding (a CDN/WAF, a reverse proxy with explicit `server_name` allowlists, or a cloud load balancer with host-based routing rules), or otherwise restrict network access to the proxy listener. ### References - Patched release: [`v1.84.0`](https://github.com/BerriAI/litellm/releases/tag/v1.84.0) **Discovery Credit**: Le The Thang (KCSC) and Kim Ngoc Chung (One Mount Group)

  • PYSEC-2026-388LiteLLM: Authentication Bypass via Host Header Injection2026-06-29vendor · osvUS

    ### Impact 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. **Most deployments are not affected.** The bypass is blocked by any upstream layer that validates or normalizes `Host`, such as: - a CDN or WAF, such as Cloudflare - a reverse proxy with `server_name` allowlists - a host-based load balancer **LiteLLM Cloud customers are not affected.** ### Patches Fixed in **`1.84.0`**. Upgrade to `1.84.0` or later. No configuration change is required. ### Workarounds If upgrading is not immediately possible, place the proxy behind an upstream component that validates or normalizes the `Host` header before forwarding (a CDN/WAF, a reverse proxy with explicit `server_name` allowlists, or a cloud load balancer with host-based routing rules), or otherwise restrict network access to the proxy listener. ### References - Patched release: [`v1.84.0`](https://github.com/BerriAI/litellm/releases/tag/v1.84.0) **Discovery Credit**: Le The Thang (KCSC) and Kim Ngoc Chung (One Mount Group)

07

also known as (6)

Other names and identifiers for this entity.

08

sources

Which sources assert this record, and when.

cnnvdenisa_euvdosvcert_bundnvdNVDCVE.orgMITRE
published 2026-06-22modified 2026-10-25
09

references (9)

External citations — patches, advisories, analysis.

scry

Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.

Free scan