TrustAI-laboratory / ASCII-Smuggling-Hidden-Prompt-Injection-DemoLinks
ASCII Smuggling Hidden Prompt Injection is a novel approach to hacking AI assistants using Unicode Tags. This project demostrate how to use Unicode Tags to hide prompt injection instruction to bypass security measures and inject prompts into large language models, such as GPT-4, leading them to provide unintended or harmful responses.
☆18Updated last year
Alternatives and similar repositories for ASCII-Smuggling-Hidden-Prompt-Injection-Demo
Users that are interested in ASCII-Smuggling-Hidden-Prompt-Injection-Demo are comparing it to the libraries listed below
Sorting:
- Manual Prompt Injection / Red Teaming Tool☆46Updated last year
- BlueSky OSINT Tool☆14Updated 11 months ago
- ☆28Updated 2 years ago
- An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for autho…☆21Updated 6 months ago
- a hackbot proof-of-concept☆40Updated last year
- An example vulnerable app that integrates an LLM☆25Updated last year
- This repository contains various attack against Large Language Models.☆119Updated last year
- ATHI — An AI Threat Modeling Framework for Policymakers☆56Updated 2 years ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆52Updated last year
- ☆10Updated 2 years ago
- ☆14Updated last year
- Daily updates from leaked data search engines, aggregators and similar services.☆125Updated this week
- ☆41Updated 8 months ago
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆42Updated last year
- ☆69Updated 3 weeks ago
- Simple Chatbot for testing AI Red Team tooling☆14Updated 9 months ago
- My inputs for the LLM Gandalf made by Lakera☆48Updated 2 years ago
- Hacking the Singularity. Deep learning hacking. Weaponizing AI in Offensive security☆105Updated last year
- An interactive CLI application for interacting with authenticated Jupyter instances.☆55Updated 6 months ago
- Automated vulnerability discovery and annotation☆67Updated last year
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆79Updated 6 months ago
- ☆18Updated 7 months ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆115Updated last year
- This project provides a set of Google Apps Scripts designed to help you identify and analyze potentially malicious domains directly from …☆14Updated last year
- Social Links API: description, examples, trial access☆72Updated 7 months ago
- PWN is an open security automation framework that aims to stand on the shoulders of security giants, promoting trust and innovation.☆67Updated this week
- All of our GitHub Actions rolled into one. Or as we like to say: One GitHub Action to rule them all!☆21Updated 2 years ago
- This is a repository to experiment with MCP for security☆45Updated 9 months ago
- Who We Are☆20Updated last year
- 🤖 A GitHub action that leverages fabric patterns through an agent-based approach☆33Updated 10 months ago