Raw vector
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-59822 is a high-severity Improper Authentication (CWE-287) vulnerability in Litellm Litellm. Its CVSS base score is 8.8 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 16th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as LLM Application Platforms; in the Protocol-Specific Risks risk domain.
The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and IA-2 (Identification and Authentication (Organizational Users)) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-42359
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, llm, openai, mcp, mcp
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The vulnerability is an authentication bypass in a publicly exposed proxy/gateway endpoint (MCP Streamable HTTP), allowing unauthenticated attackers to reach internal tooling. This directly maps to T1190 (Exploit Public-Facing Application).
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
- 14 hardening rules · 5 OS baselines
V6.4.4V6.5.4V6.5.5V6.5.7
Mitigating Controls (NIST 800-53 r5) AI
Directly enforces authentication and authorization decisions before permitting access to the MCP Streamable HTTP endpoint, blocking the fabricated Authorization header bypass.
Requires identification and authentication of all users (including via API keys) prior to granting access, preventing the unauthenticated passthrough to MCP tooling.
Enforces boundary protection and traffic filtering at the proxy/gateway layer to reject requests lacking valid LiteLLM authentication before they reach internal MCP functions.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Directly requires authentication of users/services/hardware, which eliminates missing authentication for critical functions.
PR.AA-04 directly enables verification of identity assertions (mostly preventing CWE-287 in that scope) yet leaves many other authentication failure modes unaddressed (only partial prevention overall).
PR.AA-01 supplies and governs credentials/tokens that authentication relies on, removing some weak-credential cases, yet leaves verification logic, missing checks, and protocol flaws untouched.
PR.AA-02 ensures valid enrollment and unique credential binding, which reduces some improper-auth risks at issuance time but leaves runtime claim verification untouched, so each direction only partially addresses the other.
Defining and enforcing authorizations assumes prior authentication and therefore only partially mitigates the absence of authentication.
Protecting networks from unauthorized access can be undermined by missing authentication but does not address the root authentication gap.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Requiring authentication methods whose strength matches the sensitivity of the data and mandating multi-factor authentication directly blocks attempts to access resources without proving identity.
Verifying user identity before issuing replacement credentials and forcing changes after compromise reduces the likelihood that authentication bypass can be achieved through stolen or weak credentials.
Mandating segregated approval and oversight for non-human identities reduces the chance that weak or orphaned credentials can be exploited for unauthorized authentication.
Mandating authentication requirements for critical functions at the requirements-gathering stage ensures that essential operations are not left unprotected by missing login or verification mechanisms.
Requiring authentication mechanisms and technical parameters for secure connections ensures that network services verify user identity before granting access, preventing exploitation of missing or weak authentication.
Security requirements specified early and verified through testing drive the consistent implementation of authentication mechanisms, decreasing the likelihood that authentication steps are omitted or incorrectly applied.