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

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• 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.

From the GitHub advisory

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/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.

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 servername allowlists - a host-based load balancer

Weakness type: CWE-290.

Product: litellm (PyPI) · Assigned by: GitHub_M · Published: 2026-06-22

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Attack requirements: present (depends on deployment conditions)
• Privileges required: none (no login)
• User interaction: none

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• 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.

Timeline

• 2026-06-16 — GitHub-reviewed advisory GHSA-4xpc-pv4p-pm3w published (critical)
• 2026-06-22 — CVE record published by GitHub_M
• 2026-07-15 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-4xpc-pv4p-pm3w github.com
2. CVE.org record CVE-2026-49468 cve.org
3. NVD entry CVE-2026-49468 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. access.redhat.com access.redhat.com
4. RHBZ#2491520 bugzilla.redhat.com
5. security.access.redhat.com security.access.redhat.com
6. github.com github.com
7. github.com github.com
8. pypi.org pypi.org

Critical PyPI advisories · Today’s Security Digest