CVE WatchSep 3, 2026

CVE-2026-59822

BerriAI LiteLLM Improper Authentication Vulnerability

CVSS

8.2

High

EPSS

0.5%

p42

KEV

YES

Sep 2, 2026

Exploit Today

0-100

Published: Jul 8, 2026 · Last modified: Sep 3, 2026 · CWE-287 · CWE-306

EPSS · 30d

0.2%EPSS · 30 days0.5%

2026-08-052026-09-02

KEV catalog record

Product

BerriAI / LiteLLM

Vulnerability

BerriAI LiteLLM Improper Authentication Vulnerability

Added to KEV

Sep 2, 2026

Remediate by

Sep 16, 2026

Known ransomware use

Summary description

BerriAI LiteLLM contains an improper authentication vulnerability in the MCP Streamable HTTP endpoint that could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.

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.

Notes

https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95q ; BOD 26-04: https://www.cisa.gov/news-events/directives/bod-26-04-prioritizing-security-updates-based-risk ; Forensics Triage Requirements: https://www.cisa.gov/news-events/directives/bod-26-04-implementation-guidance-prioritizing-security-updates-based-risk ; https://nvd.nist.gov/vuln/detail/CVE-2026-59822

Technical 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.

Official references

Related CVEs

CVECVSSEPSSKEVRExploitTitleMod.

CVE-2026-84452—

—

——0Windows ML CLI is a command line tool for building portable, performant, and high-quality AI models for Windows ML. Prior to 0.4.0, the src/winml/modelkit/serve/cli_api.py component exposes WinML CLI commands through a localhost HTTP API without authentication and configures the allow_origins setting as a wildcard in both src/winml/modelkit/serve/cli_api.py and src/winml/modelkit/serve/app.py. A malicious website loaded by a user can send cross-origin requests to /v1/cli/build or /v1/cli/config and set the trust_remote_code parameter to true, which is converted to the --trust-remote-code command-line flag without validation. This reaches AutoConfig.from_pretrained with trust_remote_code=True in src/winml/modelkit/loader/_autoconfig.py and imports Python code from an attacker-controlled model repository, resulting in arbitrary code execution as the server user. This issue is fixed in version 0.4.0.19h CVE-2026-848406.5 MED

—

——0A vulnerability was identified in tsi-coop tsi-dpdp-cms up to 0.5.0. This affects an unknown part of the file InterceptingFilter.java of the component Bootstrap Setup Endpoint. The manipulation leads to missing authentication. The attack can be initiated remotely. The exploit is publicly available and might be used. Upgrading to version 0.5.1 is able to mitigate this issue. Upgrading the affected component is recommended.20h CVE-2026-848395.3 MED

—

——0A vulnerability was determined in tsi-coop tsi-dpdp-cms up to 0.5.0. Affected by this issue is some unknown functionality of the file web.xml of the component Admin Console/DPO Compliance Console. Executing a manipulation can lead to missing authentication. It is possible to launch the attack remotely. The exploit has been publicly disclosed and may be utilized. Upgrading to version 0.5.1 can resolve this issue. It is suggested to upgrade the affected component.20h CVE-2026-536499.6 CRI

—

——0Joro is a web exploitation framework. Prior to version 1.1.1, Joro's default proxy mode exposes a local API on 127.0.0.1:9090 that performs no authentication and applies a wildcard CORS policy. Because plugin uploads use the CORS-safelisted multipart/form-data content type, cross-origin JavaScript on any page the operator visits can reach privileged endpoints - including uploading a native plugin and triggering a restart - directly through the operator's browser, with no preflight or credentials. Since plugins execute on load, this yields unauthenticated remote code execution as the operator's user from a single page visit. This issue has been patched in version 1.1.1.21h CVE-2025-154815.3 MED

—

——0The Notification Bar for WordPress plugin through 1.1.8 exposes an unauthenticated CSV export script that discloses all stored subscriber emails.1d CVE-2024-7956—

—

——0A vulnerability exists in the affected products that allows a threat actor to gain access to user’s projects. To exploit this vulnerability the threat actor must have basic user privileges. If exploited, the threat actor can modify and delete the project.23h