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

Free security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…

FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)

Uses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports…

AI-driven CLI for testing Android and iOS apps using natural language. Generates, runs, and fixes end-to-end tests on emulators/simulators with…

Full-stack security OS for AI agents with five-layer defense-in-depth architecture covering foundation scan, input sanitization, cognition…


Evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…

Host-agnostic pre-write security hook for coding agent: detects user-input patterns via Semgrep and emits deterministic, no-LLM security guidance.

AI Prompt Secret Scanner: local proxy and Claude Code hook that blocks secrets before they reach AI APIs

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

This technical research and review is for educational purposes on public code and constitutes Fair Dealing under the Copyright Act (Canada).

This repository contains the official implementation of the paper "[Safety in Batches? Understanding and Mitigating Safety Failures in Batch…

Technical vulnerability analysis and proof-of-concept for CVE-2026-47630, an arbitrary dlopen via TRITON_BATCH_STRATEGY_PATH in NVIDIA Triton…

A curated collection of resources for learning and researching LLM prompt injection attacks, defenses, and security.

Your personal AI assistant at all-in 888KiB (~35KB in app code). Running on an ESP32. GPIO, cron, custom tools, memory, and more.

image scaling attacks for multi-modal prompt injection

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks