Osinton

Osinton Osinton is an open-source OSINT Open Source Intelligence tool designed to perform structured investigations on individuals using publicly available information. The project allows users to search, correlate, and analyze digital footprints such as names, usernames, email addresses, and pho...

sdk

@cosignet/sdk Cliente TypeScript ligero y sin dependencias para Cosignet — aprobación humano en el bucle para acciones de agentes de IA de alto riesgo, con firmas de passkey vinculadas al payload. Ponga a un humano en el bucle antes de que se ejecute una acción peligrosa: pausarla, obtener una...

Orbit Tracer

Orbit Tracer Orbit Tracer Security Agent for Intelligent Security Remediation Automate security vulnerability analysis, risk assessment, and remediation across your entire codebase using AI and Orbit's knowledge graph The Problem Security teams face a critical challenge: Finding vulnerabilities i...

third-thoughts

Third Thoughts A Lightless Labs research project studying AI agent behavior at scale through multi-disciplinary corpus analysis basically, throwing stuff at the wall and seeing what sticks. Named after Tiffany Aching's concept from Discworld: first thoughts agents thinking, second thoughts agents...

interrogation-game

Interrogation A voice-based detective interrogation game. You're a detective. Mistral is a suspect who's lying. Your job is to catch the lie through questioning alone. Every case is procedurally generated — a unique white-collar crime, suspect, cover story, and one hidden lie. The suspect is play...

CVE-2025-67511

CVE-2025-67511: Tricking a Security AI Agent Into Pwning Itself Hacktive Security blog post for CVE-2025-67511 Blog Post Link : https://www.hacktivesecurity.com/blog/2025/12/10/cve-2025-67511-tricking-a-security-ai-agent-into-pwning-itself/ TL;DR A command injection vulnerability in the function...

StegoScan

StegoScan Overview StegoScan.py is a powerful, next-generation tool for automated steganography detection in websites, web servers, and local directories, integrating AI-driven object and text recognition with deep file analysis. Unlike traditional steganography detection tools that focus on a...

delirium-ai-safety-benchmark

Delirium AI Safety Benchmark A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion ACE and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention...

RTTM

Real Time Threat Monitoring Tool V2.0 Monitoring possible threats of your company on Internet is an impossible task to be achieved manually. Hence many threats of the company goes unnoticed until it becomes viral in public. Thus causing monetary/reputation damage. This is where RTTM comes into...

SafeForge

SafeForge – Where Apps Are Built with Trust SafeForge is an open-source mobile app hub built on GitLab that allows developers to build, upload, share, and collaborate on mobile applications in a secure, AI-verified, and fully encrypted ecosystem. Every application submitted to SafeForge is analyz...

authproof-sdk

AuthProof SDK AuthProof is a cryptographic delegation protocol for agentic AI. Most protocols in this space enforce against an operator-defined policy -- giving the operator authority to expand or reinterpret the user's original intent after the fact. AuthProof is built around a different trust...

CVE-2026-2472-Vertex-AI-SDK-Google-Cloud

🚨 CVE-2026-2472-Vertex-AI-SDK-Google-Cloud - Simple Proof of Concept Tool 🛠 About This Application This tool shows a technical proof of concept PoC for the security issue CVE-2026-2472. The issue affects the Vertex AI Python SDK from Google Cloud Platform. It relates to an unauthenticated and...

pgadmin-ai-assistant-sql-injection-cve-2026-17351-lexer-differential-bypass

CVE-2026-17351 — pgAdmin 4 AI Assistant Read-Only Bypass via Lexer Differential PoC for CVE-2026-17351, a critical CVSS 9.0 SQL injection bypass in pgAdmin 4's AI Assistant. Vulnerability Summary pgAdmin 4 versions 9.13 through 9.16 use Python's sqlparse library to validate that LLM-generated SQL...

Recon-Scan

Recon-Scan ReconScan is a open-source passive recon scanner with a FastAPI backend, async worker pipeline, and a single-page frontend. You can check the deployed site at https://recon-scan.vercel.app/ The point is fast signal: run a scan, get module-by-module findings, and get an AI summary that...

CVE-2026-41472-POC

CyberPanel XSS to RCE CVE-2026-41472 One-click Remote Code Execution in CyberPanel v2.4.3 via unauthenticated API endpoints. Overview This exploit chains multiple vulnerabilities in CyberPanel's AI Scanner feature: 1. Unauthenticated Database Injection /api/ai-scanner/callback accepts arbitrary...

veinmind-tools

veinmind-tools Documentación veinmind-tools es un conjunto de herramientas de seguridad para contenedores desarrollado por Chaitin Technology, incubado por el equipo Muyun, y construido sobre veinmind-sdk veinmind, cuyo nombre en chino es 问脉 Wenmai, que significa tomar el pulso de la seguridad en...

Zhilly

AI Pentester Assistant 🛡️ Zhilly AI Pentester Assistant AI-Powered, Portable Cyber Security & Cyber Interaction Tool Yapay Zeka Destekli, Taşınabilir Siber Güvenlik ve Siber Etkileşim Aracı 🇬🇧 English • 🇹🇷 Türkçe • ⚡ Web Flasher 🇬🇧 English / English Version 📖 About the Project This project is an...

prosey

Prosey Prosey is a CLI tool to download and display video transcriptions from YouTube, so you can get the information you're looking for without wasting hours. The main use cases are: Summarize a YouTube video and display it in the CLI with a single command quicker. Read video captions, formatted...

Awesome-MoAI-Security

Awesome Mobile On-Device AI Security SoK: Attack and Defense Landscape of Mobile On-device AI Systems Mobile on-device AI systems execute AI models locally through ML frameworks such as LiteRT/TFLite , Core ML , ExecuTorch , ONNX , and hardware-backed accelerators. This repo tracks the security...

FUCKER

FUCKER Windows-native penetration testing framework written in Go. Modular architecture with AI-driven decision engine OpenAI-compatible API. Build root@kitploit: go build -ldflags="-X main.version=$git describe --tags" -o FUCKER.exe ./cmd/fucker/ Cross-compile: root@kitploit: GOOS=linux...