BerriAI LiteLLM Improper Authentication Vulnerability
BerriAI — litellm
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.
8.8
0.5%
Vector breakdown
- Attack vector
- Network
- Attack complexity
- Low
- Attack requirements
- None
- Privileges required
- None
- User interaction
- None
- Confidentiality (Vulnerable System)
- High
- Integrity (Vulnerable System)
- Low
- Availability (Vulnerable System)
- None
- Confidentiality (Subsequent System)
- None
- Integrity (Subsequent System)
- None
- Availability (Subsequent System)
- None
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N
- Published
- Jul 8, 2026
- Modified
- Sep 3, 2026
- Added to KEV
- Sep 2, 2026
- Federal patch due
- Sep 16, 2026
CISA required action
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.
Weakness classification
Proof-of-concept & exploitation references
Weaponization
Public repositories whose name or description references CVE-2026-59822, found via a live GitHub search at request time. These are community-sourced signals, not a verified working exploit - cross-check each one before relying on it, and treat higher star counts and recent activity as (weak) corroboration, not proof.
No public GitHub repositories referencing CVE-2026-59822 were found at last check. Absence here is not proof no exploit exists - see the references below for vendor advisories and write-ups.
References
Frequently asked questions
What is CVE-2026-59822?
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.
How severe is CVE-2026-59822?
CVE-2026-59822 has a CVSS base score of 8.8 out of 10 (CVSS 4.0).
Is CVE-2026-59822 actively exploited in the wild?
Yes. CVE-2026-59822 is listed in the CISA Known Exploited Vulnerabilities (KEV) catalog, added Sep 2, 2026, meaning CISA has confirmed evidence of active exploitation.
What is the EPSS score for CVE-2026-59822?
0.5% - meaning FIRST.org's EPSS model estimates a 0.5% probability this vulnerability will be exploited in the wild within 30 days (42% percentile among all scored CVEs).
What type of vulnerability is CVE-2026-59822?
CVE-2026-59822 is classified under CWE-287, CWE-306 (CWE-287: Improper Authentication).
Cross-checked against
Impactr finds and proves whether CVE-2026-59822 - or flaws like it - are actually reachable in your own web apps and APIs, with a reproducible exploit as evidence.
Join the waitlist