CVE-2026-59822 | THREATINT

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.

PUBLISHED Reserved 2026-07-07 | Published 2026-07-08 | Updated 2026-07-09 | Assigner GitHub_M

HIGH: 8.8CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N

Problem types

CWE-287: Improper Authentication

CWE-306: Missing Authentication for Critical Function

Product status

< 1.84.0

affected

References

github.com/...itellm/security/advisories/GHSA-7488-6r32-c95q

github.com/BerriAI/litellm/pull/26463

github.com/...ommit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c

github.com/BerriAI/litellm/releases/tag/v1.84.0

cve.org (CVE-2026-59822)

nvd.nist.gov (CVE-2026-59822)

Download JSON