cve.bz

CVE-2026-49468 litellm litellm: Authentication Bypass by Spoofing

9.5 criticalEPSS 3.0%Fix available

Critical (9.5) in litellm litellm. EPSS 3.0% estimated probability of exploitation activity in the next 30 days. Fixed in litellm 1.84.0.

On this page
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.

Severity

CVSS 4.0

9.5 critical
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

CVSS 3.1

9.8 critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS
3.0% (unchanged from 3.0% a week ago; 3.0% 30 days ago) estimated probability of exploitation activity in the next 30 days; 88th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: total, assessed 2026-06-23. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-290 Authentication Bypass by Spoofing
OWASP Top 10
A07:2025 Authentication Failures
Published
Modified
NVD analysis
Analyzed, since modified
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-49468 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-49468?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-49468?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-49468 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
litellm:litellmbefore 1.84.0

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-4xpc-pv4p-pm3wPyPIlitellm<1.84.01.84.0
PYSEC-2026-388PyPIlitellm<1.84.01.84.0

Red Hat

Red Hat rates this Important.

Red Hat's statement

The vulnerability is rated with Important severity due to the limited attack surface in our default deployment configuration.

While the affected images ship with a vulnerable version of litellm, the specific vulnerability is restricted solely to proxy management-route authentication. By default, these images do not start the LiteLLM proxy server. Instead, the default entrypoints are configured to run OGX, the MLflow server (with the AI Gateway disabled), Garak evaluation jobs, or Lightspeed/Llama Stack APIs. The proxy auth bypass is not reachable unless an administrator separately deploys litellm --config from the container.

For Red Hat OpenShift AI and Ansible Automation Platform products, the severity has been set to low since these products include litellm as a dependency in some images but do not run the LiteLLM proxy in default configurations, hence the vulnerable code path is not exposed.

Red Hat's mitigation

To mitigate the risk of unauthenticated access, restrict network access to the LiteLLM proxy's management routes. Configure network firewalls or security groups to permit inbound connections only from trusted internal networks. This operational control limits the exposure of vulnerable endpoints to unauthorized external access. If the LiteLLM proxy is deployed behind a load balancer or API gateway, ensure these components are configured to strictly validate and sanitize the HTTP Host header before forwarding requests.

ProductPackageStateAdvisory
Exploit Intelligenceexploit-intelligence-tech-preview/vulnerability-analysis-rhel9Affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-26/lightspeed-chatbot-rhel9Fix deferred
Red Hat Ansible Automation Platform 2ansible-automation-platform-27/lightspeed-chatbot-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-llama-stack-core-rhel9Fix deferred
Red Hat OpenShift AI (RHOAI)rhoai/odh-mlflow-rhel9Affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9Fix deferred

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-49468.

GitHub PoC

Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it. How Harbor Check reads them, and what it found.

Detection rules

Ways to detect this CVE, not exploit code: the nuclei template that checks a system for it, and the Suricata and Snort rules that name it. A rule set may ship a rule turned off, so check yours by its sid.

Attack patterns (CAPEC)

  • CAPEC-21 Exploitation of Trusted Identifiers Likelihood: High · Severity: High
  • CAPEC-22 Exploiting Trust in Client Likelihood: High · Severity: High
  • CAPEC-59 Session Credential Falsification through Prediction Likelihood: High · Severity: High
  • CAPEC-60 Reusing Session IDs (aka Session Replay) Likelihood: High · Severity: High
  • CAPEC-94 Adversary in the Middle (AiTM) Likelihood: High · Severity: Very High
  • CAPEC-459 Creating a Rogue Certification Authority Certificate Likelihood: Medium · Severity: Very High
  • CAPEC-461 Web Services API Signature Forgery Leveraging Hash Function Extension Weakness Severity: High
  • CAPEC-473 Signature Spoof
  • CAPEC-476 Signature Spoofing by Misrepresentation Likelihood: Low · Severity: High
  • CAPEC-667 Bluetooth Impersonation AttackS (BIAS) Likelihood: Medium · Severity: High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON