Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-49468 – Authentication Bypass – LiteLLM prior to 1.84.0

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-49468 is a critical authentication bypass vulnerability (CVSS 3.1: 10.0) in LiteLLM (BerriAI), an open-source AI Gateway proxy server used to route requests to LLM APIs. A flaw in Host header parsing allows unauthenticated remote attackers to manipulate the authentication layer into evaluating a different route than the one the framework dispatches, granting access to protected management endpoints without credentials. All self-hosted LiteLLM deployments running versions prior to 1.84.0 that are directly internet-exposed are at risk.

Technical details

  • Root cause: The authentication layer in litellm/proxy/auth/auth_utils.py::get_request_route() derives the evaluated route from request.url.path, which Starlette reconstructs using the HTTP Host header. A specially crafted Host header can cause the authentication gate to evaluate a different route than FastAPI actually dispatches, enabling a full authentication bypass (CWE-290: Authentication Bypass by Spoofing).
  • Trigger conditions: An attacker sends an HTTP request containing a manipulated Host header to a LiteLLM instance that is not protected by an upstream CDN, WAF, or reverse proxy configured to normalize Host headers.
  • Attack vector: Remote, unauthenticated network access with no user interaction required; low attack complexity.
  • Impact: Unauthenticated access to protected management routes, directly exposing LLM provider API credentials (OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, and others) and gateway configuration data. Because LiteLLM acts as a centralized proxy for multiple AI providers, a single compromised instance can expose credentials across all connected downstream services simultaneously.

Affected software

  • LiteLLM (BerriAI): all versions prior to 1.84.0

Severity

CVSS v3.1 base score: 10.0 (Critical)
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Mitigation and recommended actions

  • Immediate: Upgrade LiteLLM to version 1.84.0 or later, which contains the vendor-provided fix.
  • Interim mitigation (if patching is not immediately feasible): Place LiteLLM behind a CDN, WAF, or reverse proxy configured to normalize or strictly validate the Host header before requests reach the application. Deployments with such upstream controls in place are resistant to this attack vector.
  • LiteLLM Cloud deployments managed by BerriAI are not affected by this vulnerability.

IONIX Status

The IONIX research team is tracking ongoing exploitation attempts and recommends immediate patching. Potentially affected assets are outlined in this post.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge