Login
mcp-scan – Real-Time Guardrail Monitoring and Dynamic Proxy for MCP Servers
mcp-scan is a dynamic proxy and guardrail monitor for MCP servers, providing real-time traffic inspection and enforcement for agents and tools.
Reading view
Red Teaming LLMs 2025 – Offensive Security Meets Generative AI
Offensive red teaming of large language models (LLMs) in 2025 – actionable tactics, case studies, and CISO controls for GenAI risk
mcp-scanner – Python MCP Scanner for Prompt-Injection and Insecure Agents
mcp-scanner: Python tool to scan Model Context Protocol servers for prompt injection, jailbreaks, and insecure tool patterns.
LLM Black Markets in 2025 – Prompt Injection, Jailbreak Sales & Model Leaks
Explore how LLM black markets in 2025 trade prompt jailbreaks, model leaks & exploit tools, insight for red teams, CISOs & threat intel.
AIPentestKit – AI-Augmented Red Team Toolkit for Recon, Fuzzing and Payload Generation
AIPentestKit bundles AI helpers for red teams: Burp plugins, payload and wordlist generators, webshell bypass tools and a tasklist analyzer driven by large language models.
HexStrike AI – Multi-Agent LLM Orchestration for Automated Offensive Security
HexStrike AI orchestrates LLM agents to run 150+ offensive security tools, automating reconnaissance, exploit selection and campaign execution.
LLAMATOR – Red Team Framework for Testing LLM Security
LLAMATOR is a Python framework for red teaming large language model systems with preset attacks, multi-client adapters, and reportable results.
Generative AI in Social Engineering & Phishing in 2025
Explore how generative AI is reshaping phishing in 2025, from deepfake romance frauds to voice deepfakes targeting officials, and what defenders can do now.
PyRIT – AI-Powered Reconnaissance for Cloud Red Teaming
Use PyRIT for automated reconnaissance against Azure environments with GPT-4 integration. A unique red team recon tool built by Microsoft.
