CVE-2026-59822: high-severity vulnerability in BerriAI litellm
LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
Prioritize patching. It under exploitation confirmed by CISA, has an official Brazilian government alert and has a public proof of concept.
Brazil's federal government published an alert, recommendation or bulletin that cites this vulnerability.
- CISC Gov.br · 09 Sep 2026Boletim do CISC de Vulnerabilidadesread on gov.br ↗
Official vendor statements in CSAF/VEX format: whether their product is affected, already fixed, or ruled out — and why. These are the vendor's assertions, not Vexday's judgment.
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.
LiteLLM, a proxy server for AI APIs, had a flaw where attackers could use fake authentication headers to bypass security checks and access MCP tools without a valid key. This allowed unauthorized users to make requests they shouldn't be able to make.
The vulnerability exists in the MCP Streamable HTTP endpoint where a malformed Authorization header triggers an OAuth2 passthrough fallback mechanism that replaces proper LiteLLM key validation with an empty UserAPIKeyAuth() object. An unauthenticated attacker can exploit this authentication bypass to reach protected MCP tooling without providing valid credentials, affecting systems running versions prior to 1.84.0.
In the same product, most dangerous first.