LiteLLM Vulnerability Chain Lets Low-Privilege Users Take Over AI Gateway Servers

A default low-privilege account on a LiteLLM proxy can climb to full admin and run code on the server by chaining three vulnerabilities, researchers at Obsidian Security disclosed LiteLLM is a widely deployed open-source AI gateway that brokers calls to more than 100 model providers behind one...

CVE-2026-9372

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

CVE-2026-9372

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

CVE-2026-9372 ItzCrazyKns Vane Model Provider API route.ts server-side request forgery

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

EUVD-2026-31586

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

CVE-2026-9372

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

CVE-2026-9372 ItzCrazyKns Vane Model Provider API route.ts server-side request forgery

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

CVE-2026-9372

ItzCrazyKns Vane (up to 1.12.1) contains a server-side request forgery in src/app/api/providers/route.ts via baseURL argument manipulation. Remote exploitation is possible and the exploit has been published. The project was informed early via an issue report but has not responded. No remediation ...

Vane 代码问题漏洞

Vane is a privacy-oriented AI chat engine developed by Kushagra Srivastava. It supports both local and cloud models. Versions of Vane prior to 1.12.1 contained code vulnerabilities. These vulnerabilities stemmed from unknown code in the Model Provider API component’s file...

PT-2026-42933

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

CVE-2026-39411 LobeHub has an unauthenticated authentication bypass on `webapi` routes via forgeable `X-lobe-chat-auth` header

LobeHub is a work-and-lifestyle space to find, build, and collaborate with agent teammates that grow with you. Prior to 2.1.48, the webapi authentication layer trusts a client-controlled X-lobe-chat-auth header that is only XOR-obfuscated, not signed or otherwise authenticated. Because the XOR ke...

CVE-2026-32002

OpenClaw versions prior to 2026.2.23 contain a sandbox bypass vulnerability in the sandboxed image tool that fails to enforce tools.fs.workspaceOnly restrictions on mounted sandbox paths, allowing attackers to read out-of-workspace files. Attackers can load restricted mounted images and exfiltrat...

CVE-2026-32002

OpenClaw is affected in versions prior to 2026.2.23. The sandboxed image tool fails to enforce tools.fs.workspaceOnly restrictions on mounted sandbox paths, allowing reading of out-of-workspace files. Attackers can load restricted mounted images and exfiltrate them via vision model provider reque...

CVE-2025-67732 Dify Vulnerable to Plaintext API Key Exposure via Model Provider Configuration Endpoint

Dify is an open-source LLM app development platform. Prior to version 1.11.0, the API key is exposed in plaintext to the frontend, allowing non-administrator users to view and reuse it. This can lead to unauthorized access to third-party services, potentially consuming limited quotas. Version...

CVE-2025-67732

Dify (open-source LLM app platform) prior to v1.11.0 exposes API keys in plaintext to the frontend, allowing non-administrator users to view and reuse them. This can enable unauthorized access to third‑party services and potential quota abuse. A fix is available in v1.11.0 or later.

SONNI: Secure Oblivious Neural Network Inference

In the standard privacy-preserving Machine learning as-a-service MLaaS model, the client encrypts data using homomorphic encryption and uploads it to a server for computation. The result is then sent back to the client for decryption. It has become more and more common for the computation to be...