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

KLAIOS is a hybrid security environment that merges Kali Linux’s offensive toolkit with hardened, VPN-bunker-style isolation—enhanced by modern AI…

OsintNET is a browser-based OSINT platform for domain intelligence, website risk scanning, SERP discovery, image intelligence and AI image detection.

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

All the materials for Gareth Heyes' Black Hat talk: CSS: the bomb inside your inbox.

Reproducible AI-assisted vulnerability rediscovery of CVE-2026-42945 in nginx, including technical analysis, PoC trigger, and patch validation for…

Measuring and closing the text–vector integrity gap in offline RAG: margin law, vector-database audits and code-level verification.

Automated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…

A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench,…


Ultrafast CLI on Apple Silicon macOS for fast, sandboxed development and LLM agents.

Code, derived data and results for: Evaluating Baseline Detectors of Hijacked LLM Agents Under Rare Attacks and Distribution Shift

Secure local REST, CLI, MCP, and agent bridge for IDA Pro 9.x

AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.

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

Just-in-time API keys for AI agents - and any other process you route through it: the caller only ever sees a placeholder.

LLM-backed AI agent security — inbound injection detection + outbound privacy protection

Read-only safety scanner for Claude Code projects. Catches CVE-2025-59536, statusLine injection, prompt injection, and more.

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…