# CVE-2026-59822

## Summary

- **CVE ID:** CVE-2026-59822
- **Severity:** HIGH
- **CVSS Score:** 8.8 (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)
- **CWE:** CWE-287, CWE-306
- **Published:** Jul 8, 2026
- **Last Modified:** Sep 3, 2026

## Description

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.

## Affected Products

- BerriAI — litellm (< 1.84.0)

## References

- [CNA](https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q)
- [CNA](https://github.com/BerriAI/litellm/pull/26463)
- [CNA](https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c)
- [CNA](https://github.com/BerriAI/litellm/releases/tag/v1.84.0)
- [CISA-ADP](https://www.wiz.io/blog/ai-infrastructure-honeypot)
- [CISA-ADP](https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.87%
- **EPSS Percentile:** 56.7

## Known Exploited Vulnerabilities (KEV)

- **Date Added:** Sep 2, 2026
- **Due Date:** Sep 16, 2026

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._