
masq
Live recon and posture auditing for AI agent infrastructure: scans MCP configs, session logs, and APIs for secrets, poisoned catalogs, and CoT leaks.

Live recon and posture auditing for AI agent infrastructure: scans MCP configs, session logs, and APIs for secrets, poisoned catalogs, and CoT leaks.

PhantomRecon is a CLI-based, modular, agent-driven red team automation tool designed to demonstrate autonomous offensive security workflows powered…

A tool to visually snapshot a website by supplying multiple user-agent. Designed to aid in discovery of different entry points into an application.

Multi-threaded router fingerprinting tool that identifies web-exposed network devices by analyzing HTTP responses, headers, and favicon hashes for…

Real Spaces - WordPress Properties Directory Theme <= 3.6 - Unauthenticated Privilege Escalation to Administrator

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual…

AI-powered offensive security testing using autonomous agents, directly in your terminal.

Rosemary: Cross-platform kernel-level pivoting over QUIC. No TUN/TAP. No proxychains. No proxy settings.

Curated list of categorized User Agents

Your personal intelligence agent. Watches the world from multiple data sources and pings you when something changes.

An offensive/defense security toolset for discovery, recon and ethical assessment of AI Agents

PoC CVE-2020-6308


Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

AI agent framework for black-box security testing with autonomous multi-agent orchestration, built-in pentesting tools, and MCP integration for bug…

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational…

autonomous red teaming platform; multi-agent offensive-security meta-harness