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.
CISA name: BerriAI LiteLLM Improper Authentication Vulnerability
Apply mitigations in accordance with vendor instructions, ensuring compliance with CISA’s BOD 26-04 Prioritizing Security Updates Based on Risk (see URL in Notes) guidance and CISA’s “Forensics Triage Requirements” (see URL in Notes). Follow applicable BOD 26-04 guidance for cloud services or discontinue use of the product if mitigations are unavailable. Stakeholders are responsible for evaluating each asset's internet exposure and ensuring adherence to BOD 26-04 patching guidelines.
Federal remediation due: 2026-09-16
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:NDerived from NVD CPE configurations
Schedule remediation and monitor for exploitation.
Recommendation, not a confirmed directive · score is composed only of the factors shown above