8378 matches found
SecureML
SecureAIML 🔐 Unternehmensreife KI-Modellsicherheit basierend auf OpenSSF Model Signing SecureAIML ist das „Stripe für Modellsicherheit“ – es macht den Schutz von KI-Modellen auf Unternehmensniveau für jede Organisation zugänglich, benutzerfreundlich und produktionsreif. Warum SecureAIML? Im...
CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload
SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload
SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
0-click-RCE-Exploit-for-CVE-2023-51409
CVE-2023-51409 / Exploit RCE 0-Click Autore: Joshua Provoste https://x.com/JoshuaProvoste/status/1858586463777989073 Questo repository contiene un exploit proof-of-concept per CVE-2023-51409, una vulnerabilità di caricamento file arbitrario non autenticato nel plugin WordPress AI Engine: ChatGPT...
CVE-2025-492026
Avviso di sicurezza: CVE-2025-492026 Riepilogo È stata identificata una vulnerabilità in Copilot AI che causa l'inclusione di un collegamento ipertestuale non intenzionale nella sezione "link source" ogni volta che Copilot recupera una query web. Questo problema ha portato gli utenti a cliccare s...
CVE-2025-492025
CVE-2025-492025 Avviso di sicurezza: CVE-2025-492025 Sommario È stata identificata una vulnerabilità in Copilot AI che causa l'inclusione di un collegamento ipertestuale non intenzionale nella sezione "origine del collegamento" ogni volta che Copilot recupera una query web. Questo problema ha...
binaryninja-ollama
Binary Ninja Ollama v1.0.9 Autor: Austin Haggard O Binary Ninja Ollama se integra ao seu próprio servidor ollama hospedado localmente para renomear funções e variáveis com IA Descrição: Ollama é uma ferramenta que permite baixar modelos de IA de código aberto e executá-los localmente. Alguns...
CVE-2025-63708
CVE-2025-63708 CVE-ID: CVE-2025-63708 Zugewiesen: 11-12-2025 Problemtyp: CWE-79 Cross-Site Scripting Betroffenes Produkt: „AI Font Matcher“ veröffentlicht am 2025-10-10, nid=18425 Produktseite:...
r2d2
r2d2 Plugin GPT-4 per radare2 Introduzione Questo è un plugin per radare2 che utilizza GPT-4 per consentire a GPT-4 di emettere comandi r2 e interpretarne l'output. https://github.com/dnakov/r2d2/assets/3777433/4bc7b211-bccc-4b04-9350-6bfca8989edb...
CVE-2026-14558
CVE-2026-14558 affects the WP User Frontend WordPress plugin prior to 4.3.10 . The flaw lies in the AI Form Builder component, which does not properly validate field type definitions and deserialises user-controlled post metadata when rendering submitted posts. Users with Editor-level access (or ...
Flowise-RCE-CVE-2025-59528
CVE-2025-59528 — Execução Remota de Código RCE Autenticada no Flowise AI Visão Geral ID do CVE: CVE-2025-59528 Software Afetado: Flowise AI Versões Vulneráveis: = 3.0.4 Versão Corrigida: 3.0.5 e posterior Severidade: Crítica Autor: r3nsi15 Data: 2025 Descrição As versões do Flowise AI até 3.0.4...
sqlmap-ai
Assistente de IA para SQLMap Um wrapper com tecnologia de IA em torno do SQLMap que torna os testes de injeção SQL mais acessíveis e automatizados. Recursos Recursos Principais Testes Assistidos por IA - Análise inteligente de vulnerabilidades e recomendações Testes Adaptativos - Testes passo a...
c4-meta-system
C4-META System v1.0.0 prototipo di ricerca Prototipo di ricerca per la difesa AI multi-livello: spiegabilità C4, classificatori ensemble, deoffuscamento, motore di sicurezza O₂, difesa ThoughtVirus e allineamento valoriale SVETILO. Grado alpha — validato internamente, audit esterno in sospeso...
jebmcp
Un server e plugin MCP rapido e sporco per JEB Pro. Testato su Cline, Cursor e RooCode. Riferimento: https://github.com/mrexodia/ida-pro-mcp Installazione Requisiti root@kitploit: Python = 3.11 uv: https://docs.astral.sh/uv/getting-started/installation/ Utilizzo COPIA il file src/jebmcp/MCP.py in...
training-security-awareness
Free Security Awareness Training for Employees — Open Source Interactive SCORM Library 130+ free, open-source security awareness training exercises for employees — hands-on, interactive SCORM modules covering phishing awareness training, GDPR, AI security, and more. Built for people who want to...
EUVD-2026-67327
The static resource interface /api/static/deployKey/ of Yu AI Code Mother v4.3 is vulnerable to path traversal. The user-controlled path is concatenated to the preview root directory without any normalization, allowing anonymous attackers to read files outside the preview root...
PyRIT
Python Risk Identification Tool für generative KI PyRIT Das Python Risk Identification Tool für generative KI PyRIT ist ein Open-Source-Framework, das Sicherheitsexperten und Ingenieure befähigt, proaktiv Risiken in generativen KI-Systemen zu identifizieren. !WARNING PyRIT hat einen neuen Standor...
CVE-2026-81847
A vulnerability was found in MAA-AI MaaMCP up to 1.1.1.dev6+g2e4a41287. The affected element is the function savepipeline/loadpipeline of the file pipelinetools.py. Performing a manipulation results in path traversal. The attack can be initiated remotely. The exploit has been made public and coul...
CVE-2026-75337
The static resource interface /api/static/deployKey/ of Yu AI Code Mother v4.3 is vulnerable to path traversal. The user-controlled path is concatenated to the preview root directory without any normalization, allowing anonymous attackers to read files outside the preview root...
EUVD-2026-67772
An OS command injection vulnerability in the killSessionSync function lib/agent-runtime.ts of 23blocks-OS ai-maestro v0.24.17 allows attackers to execute arbitrary commands via a crafted input...