#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Educational demo of three Claude Code vulnerabilities (hooks bypass, MCP injection, API key exfiltration) with attacker server, MITM proxy, and…

Extensión de Burp Suite que incorpora detección pasiva de vulnerabilidades mediante inteligencia artificial.

Benchmarking prompt injection detections for web agents.

Let AI agents explore a running game from the inside. Live, safe, instant.

StealthRL: RL framework for adversarially paraphrasing AI text to stress-test detector robustness.

AI-driven automated threat analysis pipeline that routes files, URLs, IPs, domains, or images through specialized security analyzers and generates…

A tool that checks if a TorchServe instance is vulnerable to CVE-2023-43654

MCP is being adopted rapidly. Security guidance is lagging behind. This checklist gives security engineers, platform teams, and technical leaders a…

Browser extension that detects PII and sensitive data in AI chats, masks it with placeholders before sending, and restores originals in replies—all…

Security for the modern age of AI: defend against bad AI agents and malicious npm packages

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal…

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

Volatility 3 plugin that carves MCP/JSON-RPC message candidates from Windows and Linux memory dumps, preserving raw bytes, addresses, and SHA-256 for…

Asymmetric defense against adversarial AI agents. VeilGate evaluates each incoming request, redirects suspected agents into a per-IP-consistent…

OWASP Web Security Testing Guide RAG system with ChromaDB, MCP for Claude Code

Modular security toolkit for autonomous agents providing static analysis, configuration auditing, runtime monitoring, and supply chain verification…

Explainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.

Security research on context compaction in coding agents: shows how forged role labels in untrusted content survive summarization and get executed,…