LLM red-team harness that scans for OWASP LLM Top 10 and MITRE ATLAS vulnerabilities, providing prioritized findings in table, JSON, SARIF, or via an MCP server for AI agents.
A Model Context Protocol server that exposes a hospital-oriented web application firewall engine for AI assistants. It enables request inspection against curated security rules and provides tools for rule management and security testing.
An offensive security dataset generator that creates high-quality, multi-turn penetration testing conversation datasets for fine-tuning security-focused LLMs. It enables users to generate realistic pentesting workflows featuring chain-of-thought reasoning, tool outputs, and over 45 diverse attack scenarios.
Intentionally vulnerable Model Context Protocol (MCP) server designed for security research that processes natural language queries through an LLM to execute SQL queries or shell commands without restrictions.