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

The open source coding agent.
Black-box test whether an LLM chatbot is vulnerable to markdown/HTML exfil (CVE-2025-32711 class). Spins up a sink, sends payloads, renders in…

A lightweight mcp to prevent poisoning CVE (CVE-2025-54136), researchers hijacking Claude Code/Copilot/Gemini via prompt injection, and hundreds of…

An automated, high-precision zero-shot evaluation pipeline for OpenAI's CLIP model on CIFAR-10. Features 88.80% accuracy, Safetensors security…

Serverless Framework MCP Server (CVE-2025-69256) Base Score: 9.4/10 → CTT Enhanced Score: 9.9/10 A critical command injection vulnerability in…

Security analysis tool identifying risks in Blackbox.ai extensions, including credential harvesting, unpatched CVEs, and privacy threats from hidden…

Air-gapped cybersecurity assistant for security professionals. 100% offline AI-powered analysis tool for Nmap, Volatility, BloodHound, Metasploit,…

Offline AI Security Assistant for Air-Gapped Pentesting

Real-time guardrails for Claude Code tool calls.

CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation

Evaluation framework for studying LLM agents that automatically generate working exploits from vulnerability reports, bypassing modern security…

On-device AI browser automation using WebLLM. No cloud, no API keys, fully private.

AI coding agents that can't exfiltrate secrets or merge their own PRs.

Tools for attacking Computer Use Agents

Anti-LLM obfuscation via finger counting

reverse engineering SynthID for text

A Python library for Secure and Explainable Machine Learning Documentation available @ https://secml.gitlab.io Follow us on Twitter @…

OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)