CVE Intelligence
Skip to main content
HIGHpublic exploit

CVE-2026-49468

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

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 Updated Sources: cvelistV5, GitHub_M

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the scoring sources call it.

Exploitation

Exploit code

public exploit, none observed

EPSS

3%

chance of exploitation in 30 days

Affects

berriai

4 products listed

CVSS base

8.1

HIGH

CISA SSVC assessment

Three decision points CISA publishes for the CVEs it assesses · SSVC 2.0.3. A stakeholder decision, not a severity score.

CISA

Exploitation

None

none · proof-of-concept · active

Automatable

Yes

can an attacker script all four kill-chain steps

Technical impact

Total

partial · total control of the vulnerable component

Affected scope

The catalog records vendors and products as separate lists, not pairs, so which product belongs to which vendor is not something this page can say.

Vendors (2)

berriairedhat

Products (4)

litellmexploit intelligencered hat ansible automation platform 2red hat openshift ai rhoai

Every base score collected

Sources score independently and disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactSource
8.1CVSS 3.1HIGH——cvelistV5

Weakness & attack patterns

  • CWE-290

Attack patterns reported against this CVE. The ATT&CK techniques below are inferred from its weakness class.

  • T1134Access Token Manipulation
  • T1528Steal Application Access Token
  • T1539Steal Web Session Cookie

Public exploit

Capability, not use: code existing is a different claim from anyone running it.

Indexed by

poc in github

Detection

Read off the CVSS vector and the weakness class. Starting points, not rules we have tested.

  • Search application, proxy, and WAF logs for requests touching /proxy/auth/auth_utils.py::get_request_route().

References

5 on the record

Elsewhere on this site

  • berriaievery CVE for this vendor
  • redhatevery CVE for this vendor
  • CWE-290other pages naming this weakness

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.