Repello-AI / whistleblower
Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers and folks who want to know what's going on inside the LLM-based app they use daily
☆117Updated 8 months ago
Alternatives and similar repositories for whistleblower:
Users that are interested in whistleblower are comparing it to the libraries listed below
- A CLI tool for threat modeling and visualizing AI agents built using popular frameworks like LangGraph, AutoGen, CrewAI, and more.☆181Updated last week
- A collection of resources and reading material that we recommend☆305Updated 6 months ago
- ☆25Updated 2 years ago
- Jeopardy-style CTF challenge deployment and management tool.☆75Updated last week
- An advanced yet simple attack/defence CTF infrastructure in Go☆14Updated 2 months ago
- An Open Source CTF hosting platform☆56Updated 2 months ago
- Knowledge Graph Embeddings (KGE) for RAG-LLMs. Our goal was to compare the mathematical differences between Traditional Static Multimoda…☆17Updated 2 months ago
- CTF challenges designed and implemented in machine learning applications☆146Updated 7 months ago
- ☆16Updated 6 months ago
- Adaptive AWS Zero Trust Policy made easy: Auto-generate least-privilege policies based on user activity in real time! Accelerate the adop…☆77Updated 11 months ago
- A guide to LLM hacking: fundamentals, prompt injection, offense, and defense☆148Updated 2 years ago
- ☆13Updated last year
- Learn AI security through a series of vulnerable LLM CTF challenges. No sign ups, no cloud fees, run everything locally on your system.☆279Updated 8 months ago
- ☆265Updated last year
- Payloads for Attacking Large Language Models☆81Updated 9 months ago
- Learn about a type of vulnerability that specifically targets machine learning models☆260Updated 10 months ago
- AIShield Watchtower: Dive Deep into AI's Secrets! 🔍 Open-source tool by AIShield for AI model insights & vulnerability scans. Secure you…☆191Updated last week
- Your gateway to OWASP. Discover, engage, and help shape the future!☆69Updated this week
- ☆10Updated 5 months ago
- Every practical and proposed defense against prompt injection.☆424Updated 2 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆89Updated 2 weeks ago
- Supporting resources and documentation for FLARE @ Google Summer of Code 2025☆23Updated last month
- Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.☆162Updated last year
- This repository curates a collection of monthly white papers focused on the latest LLM attack and defenses.☆22Updated 6 months ago
- ☆268Updated 9 months ago
- Personal notes (technical)☆253Updated 2 months ago
- Prompt Injections Everywhere☆118Updated 8 months ago
- Awesome AI Starups in India☆58Updated 5 months ago
- Roadmap to get started in Infosec for absolute begineer☆99Updated 11 months ago
- ☆127Updated 5 months ago