Read the docs
TI-2026-42639 Aliases CVE-2026-59822GHSA-7488-6r32-c95q

LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback

Priority CRITICAL 95Exploited in the wildCWE-287Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Attack requirements
None
Impact type
Security bypass
Confidentiality · integrity · availability
High · Low · None
Fix status
Fixed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA and GitHub. Impact type from CWE-287.

Summary

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.

Why it matters now

Exploitation Active In CISA KEV since 2026-09-02CISA due date 2026-09-16
EPSS 0.00836 57th percentileScored 2026-11-07
Fix Fixed litellm (BerriAI): 1.84.0litellm (PyPI): 1.84.0

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Active
Automatable
Yes
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
BerriAIlitellmbefore 1.84.01.84.0Patch availableCNA
—litellm (PyPI)before 1.84.01.84.0Patch availableGHSA-7488-6r32-c95q
  • litellm VendorBerriAI Affected before 1.84.0 Fixed in 1.84.0 Patch available CNA
  • litellm (PyPI) Vendor— Affected before 1.84.0 Fixed in 1.84.0 Patch available GHSA-7488-6r32-c95q

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*before 1.84.0VulnerableBerriAI
  • cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:* Versions before 1.84.0 Vulnerable ·BerriAI

Remediation

  • Fix · CNA litellm (BerriAI) Fixed in 1.84.0
  • Fix · GHSA-7488-6r32-c95q litellm (PyPI) Fixed in 1.84.0 Advisory →

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

Not affected: 4 products
  • Exploit Intelligence
  • Lightspeed Core
  • Red Hat Ansible Automation Platform 2
  • Red Hat OpenShift AI (RHOAI)

Timeline

  1. 2026-09-02 Added to CISA KEV
  2. 2026-10-02 Threatist record created from CVE-2026-59822
  3. 2026-10-03 Alias added: GHSA-7488-6r32-c95q
  4. 2026-10-16 Affected versions changed · Red Hat

References

Patch 3

Advisory 2

Other 2

  • TI-2026-26015 Trivy ecosystem supply chain briefly compromised KEVCVSS 4.0CRITICAL 9.4
  • TI-2026-30529 LiteLLM: SQL injection in Proxy API key verification KEVCVSS 4.0CRITICAL 9.3
  • TI-2026-30582 LiteLLM: Authenticated command execution via MCP stdio test endpoints KEVCVSS 4.0HIGH 8.7
  • TI-2024-05340 Remote Code Execution in BerriAI/litellm CVSS 3.1CRITICAL 9.8
  • TI-2024-02760 Server-Side Template Injection in BerriAI/litellm CVSS 3.0CRITICAL 9.8
  • TI-2026-34701 LiteLLM < 1.83.10 Privilege Escalation via User Update CVSS 4.0HIGH 8.7
See all 36 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences