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

Open-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…

Human-in-the-loop UI that converts natural-language or C/C++ protocol descriptions into a reviewable Protocol IR, then generates Sapic+/Tamarin…

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…

Evolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…

Open framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…

Plugins integrating Claude Code with IDA Pro to assist reverse engineering and binary analysis workflows through AI-driven disassembly and code…

IDA Pro plugin that uses OpenAI GPT-3.5/GPT-4 to automate reverse engineering tasks such as function naming, code explanation, and decompiled…

AI-powered security co-pilot that catches vulnerabilities as you code. Real-time security scanning, educational explanations, and auto fixes for…

Open-source cybersecurity harness to build and deploy sovereign, persistent AI security agents (sentinels) that continuously find, prove and fix…

Gemini - Production LLM Runtime Alignment Context Injection

Curated collection of LLM jailbreak prompts and bypass techniques, documenting adversarial inputs that circumvent AI model safety guardrails.

Multi-agent static application-security review harness for AI coding agents: maps codebases, hunts vulnerability classes, chains and verifies…

AI-assisted research pipeline that extracts HTTP desync techniques, generates malformed request test-cases, validates them via Burp, and confirms…

Reference implementation for "Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution". Out-of-band Epistemic Andon Cord,…

Red team framework and multi-operator C2 platform with AI agents, malleable implants, rootkits, phishing engine, and 741 CLI commands covering the…

Evidence and data for the Sorami technical report on security defaults of 15 AI serving, vector database and MCP Helm charts on Kubernetes.

Next-generation JavaScript identifier recovery with LLMs.