CVE-2026-24207

CVE-2026-24207 — NVIDIA Triton SageMaker Auth Bypass to Unauth RCE Unauthenticated attackers can reach the model-management surface of NVIDIA Triton Inference Server on the SageMaker and Vertex AI HTTP ports — bypassing the operator's --http-restricted-api configuration. Combined with the SageMak...

Welcome to the Jungle: What We Found Inside 15,465 Public MCP Servers

In 2024, MCP Model Context Protocol set out to become the USB-C of AI: one standard for connecting models, agents, and IDEs to tools and data. The protocol delivered. Thousands of developers built servers, and enterprises plugged them into agent workflows. The ecosystem around it fell short...

llama-factory-webui-rce-cve-2026-58116-trust-remote-code-model-path-injection

CVE-2026-58116 — RCE en WebUI de LLaMA-Factory mediante trustremotecode Prueba de concepto para CVE-2026-58116 CVSS 9.8 Crítico: ejecución remota de código en LLaMA-Factory = v0.9.5. La WebUI de LLaMA-Factory tiene hardcodeado trustremotecode=True al cargar un modelo...

deep-pwning

Deep-pwning 是一个轻量级的框架，用于对机器学习模型进行实验，目标是评估它们在面对有动机的对手时的鲁棒性。 请注意，当前状态的 deep-pwning 远未 达到成熟或完成。它旨在供您实验、扩展和延伸。只有这样，我们才能真正帮助它成为 统计机器学习模型的渗透测试工具包 。 背景 研究人员发现，让机器学习模型（分类器、聚类器、回归器等）做出客观上错误的决策是出乎意料地容易。这一研究领域被称为...

CVE-2025-32434

CVE-2025-32434: PyTorch RCE Vulnerability - PoC What is CVE-2025-32434? CVE-2025-32434 is a critical Remote Code Execution RCE vulnerability in PyTorch, a widely used Python library for deep learning and neural networks. The Core Problem The vulnerability exists in the torch.load function, even...

PrivacyRaven

Nota: Este proyecto está en pausa. PrivacyRaven es una biblioteca de pruebas de privacidad para sistemas de aprendizaje profundo. Puedes usarla para determinar la susceptibilidad de un modelo a diferentes ataques de privacidad; evaluar técnicas de aprendizaje automático que preservan la privacida...

CVE-2026-105753

A flaw was found in vLLM. This vulnerability allows a remote user to cause a Denial of Service DoS on the model serving engine. The issue occurs when a multimodal request is rejected after media processing, causing the frontend and backend caches to become desynchronized. A subsequent request...

tesla-security-research

Tesla Security Research Vulnerability research on the Tesla Model 3/Y infotainment system Intel Atom MCU, Linux 4.14.235, responsibly disclosed to Tesla via Bugcrowd. Obtained persistent root access on a production Tesla Model 3 through a command injection vulnerability in Tesla's ODIN diagnostic...

CVE-2023-1177

CVE-2023-1177 | | MLFlow Path Traversal | Tested on MLflow 2.2.0 | src: https://github.com/iumiro/CVE-2023-1177-MLFlow | .. code-block:: bash !/bin/bash RAND="EXPLOIT-$1+$RANDOM%9999" URL="http://172.17.0.2:6001" FILE='/root/.ssh/idrsa' curl -vX POST...

CVE-2026-105741

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.5.0 until 1.10.3, an IP spoofing vulnerability in the Model Context Protocol MCP configuration installation endpoint POST /api/v1/mcp/project/projectid/install allowed authenticated remote attackers to bypass th...

CVE-2026-105741 Langflow: IP Spoofing Bypass via `X-Forwarded-For` Allowing Remote Configuration Write

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.5.0 until 1.10.3, an IP spoofing vulnerability in the Model Context Protocol MCP configuration installation endpoint POST /api/v1/mcp/project/projectid/install allowed authenticated remote attackers to bypass th...

EUVD-2026-92800

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.5.0 until 1.10.3, an IP spoofing vulnerability in the Model Context Protocol MCP configuration installation endpoint POST /api/v1/mcp/project/projectid/install allowed authenticated remote attackers to bypass th...

CVE-2026-105741

The software Langflow (versions 1.5.0 through 1.10.3) is vulnerable to an IP spoofing issue within the Model Context Protocol (MCP) configuration installation endpoint (POST /api/v1/mcp/project/{project_id}/install). An authenticated remote attacker can bypass "local-only" access restrictions by ...

CVE-2026-105741 Langflow: IP Spoofing Bypass via `X-Forwarded-For` Allowing Remote Configuration Write

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.5.0 until 1.10.3, an IP spoofing vulnerability in the Model Context Protocol MCP configuration installation endpoint POST /api/v1/mcp/project/projectid/install allowed authenticated remote attackers to bypass th...

CVE-2026-105741 Langflow: IP Spoofing Bypass via `X-Forwarded-For` Allowing Remote Configuration Write

Langflow is a tool for building and deploying AI-powered agents and workflows. From 1.5.0 until 1.10.3, an IP spoofing vulnerability in the Model Context Protocol MCP configuration installation endpoint POST /api/v1/mcp/project/projectid/install allowed authenticated remote attackers to bypass th...

mcp-attack-detection-sentinel

Detección de ataques MCP — Laboratorio de investigación de Sentinel Investigación de detección de Sentinel para patrones de ataque de MCP Protocolo de Contexto de Modelo : acceso de identidad inusual tras un evento relacionado con MCP, mutación de la definición de herramientas, acceso entre...

CVE-2024-45436

Ollama CVE-2024-45436 Exploit A clean and efficient exploit implementation for the Ollama ZIP traversal vulnerability CVE-2024-45436. 中文文档：READMECN.md Vulnerability Description CVE-2024-45436 is a path traversal vulnerability also known as "Zip Slip" in Ollama versions prior to 0.1.47. The...

CVE-2026-47630

CVE-2026-47630 — NVIDIA Triton Inference Server: dlopen arbitrario mediante TRITONBATCHSTRATEGYPATH Recorrido de ruta absoluta en el cargador personalizado de estrategias de batching de triton-inference-server/core. Un parámetro de configuración del modelo se pasa sin validar a dlopenRTLDNOW |...

0

El harness de código abierto, auto-evolutivo y multi-modelo para investigación en seguridad. The Swiss Applied AI & Cybersecurity Research Lab 0.security · Documentación · FoxGuard El harness detrás de nuestros avances en investigación. Encuentra vulnerabilidades novedosas en las capas más...

Prineo_RE

About PriPara internal name Prineo is an arcade rythm game developed by SynSophia. Goal The goal of this project was to reverse the model format of the arcade series in order to port exclusive characters to the newer version of the game on Nintendo Switch. Screenshots Some interesting screenshots...