← back
CVE-2026-59822highunder attackCWE-287CWE-306

LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback

71Vexday Risk Score

Prioritize patching. It under exploitation confirmed by CISA and has a public proof of concept.

ssvc Actcvss 8.8epss 0.9%
from disclosure to weapon57 days
Published on NVDJul 8
1st PoC+57d
CISA KEV+56d
exploitation probability
0.9%top 43% of all CVEs
observed exploitation
yesCISA + VulnCheck
1 public exploit(s)
What the vendors declare (VEX)

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.

Affected
1 product
Exploit Intelligence
workaround: Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Not affected
3 products (8 components) — because the vulnerable code is not present in the product
Red Hat OpenShift AI (RHOAI) · Red Hat Ansible Automation Platform 2 · Lightspeed Core
Action required by CISAfederal deadline: 2026-09-16

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.

In short

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.

Technical detail

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.

Summary generated and translated by AI from the official 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.
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
Affected products
BerriAI · litellm
⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.