A fully open-source, LlamaCloud-backed alternative to NotebookLM

Payloads for AI Red Teaming and beyond

OWASP Foundation web repository

Keyhacks is a repository which shows quick ways in which API keys leaked by a bug bounty program can be checked to see if they're valid.

A powerful, AI Gateway designed from scratch for AI

The IBM MQ C Performance Harness

Supply-chain Levels for Software Artifacts

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Reconmap is a collaboration-first security operations platform for infosec teams and MSSPs, enabling end‑to‑end engagement management, from reconnaissance through execution and reporting. With buil…

A collection of awesome resources related AI security

Anthropic's Interactive Prompt Engineering Tutorial

New ways of breaking app-integrated LLMs

Constrain, log and scan your MCP connections for security vulnerabilities.

Application which investigates defensive measures against prompt injection attacks on an LLM, with a focus on the exposure of external tools.

Prompt Injection Primer for Engineers

Summaries, transcripts, key points, and other useful insights from AWS re:inforce 2025 talks for those of us who don't have time to watch every presentation!

An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.

Generate Frida bypass scripts for Android APK root and SSL checks.

Obtain GraphQL API schema despite disabled introspection!

🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance m…

Google Dork Scanner for Google Chrome Extension

YSDA course in Natural Language Processing

DeepTeam is a framework to red team LLMs and LLM systems.

Moonshot - A simple and modular tool to evaluate and red-team any LLM application.

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

Inspect: A framework for large language model evaluations

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML …