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☆52Updated last year
- This repository contains various attack against Large Language Models.☆128Updated last year
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆42Updated last year
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆54Updated last year
- ☆10Updated 2 years ago
- LLM | Security | Operations in one github repo with good links and pictures.☆88Updated this week
- Point of Concept: To help to automate the collection of evidence for SOC 2 Audits and etc.☆11Updated last year
- A list of OSINT resources and tools that may be useful to you when conducting investigations related to the Democratic People's Republic …☆35Updated 9 months ago
- ☆14Updated last year
- BlueSky OSINT Tool☆14Updated last year
- Hacking the Singularity. Deep learning hacking. Weaponizing AI in Offensive security☆105Updated last year
- Phishable is a project that logs misconfigured DNS that can be exploited to conduct phishing attacks & spoof domains. Phishable helps org…☆21Updated 2 years ago
- MCP server for dnstwist, a powerful DNS fuzzing tool that helps detect typosquatting, phishing, and corporate espionage.☆43Updated 11 months ago
- A collection of prompt injection mitigation techniques.☆27Updated 2 years ago
- ☆29Updated 2 years ago
- [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the vict…☆44Updated 11 months ago
- mcp scan that scans any mcp server for indirect attack vectors and security or configuration vulnerabilities☆81Updated last month
- AI Powered Terminal Based Ethical Hacking Assistant☆87Updated last year
- Who We Are☆21Updated 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
- Multi-agent system (MAS) hijacking demos☆40Updated this week
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆84Updated 9 months ago
- Daily updates from leaked data search engines, aggregators and similar services.☆146Updated this week
- An AI-powered application that conducts structured interviews to create and maintain detailed personal profiles across various life aspec…☆55Updated 10 months ago
- A small go harness that uses Ollama to orchestrate LLMs in a restricted process flow☆15Updated last year
- MalStatWare automates malware analysis with Python. Extract key details like file size, type, hash, path, and digital signature. It analy…☆30Updated last year
- a hackbot proof-of-concept☆41Updated last year
- A simple web app to get the latest EPSS data for a CVE ID☆12Updated last month
- An interactive CLI application for interacting with authenticated Jupyter instances.☆55Updated 9 months ago
- A knowledge source about TTPs used to target GenAI-based systems, copilots and agents☆135Updated last month