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☆51Updated last year
- BlueSky OSINT Tool☆14Updated last year
- This is a repository to experiment with MCP for security☆45Updated last year
- 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
- ☆20Updated 9 months ago
- Point of Concept: To help to automate the collection of evidence for SOC 2 Audits and etc.☆11Updated last year
- ATHI — An AI Threat Modeling Framework for Policymakers☆59Updated 2 years ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆54Updated 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
- Repository for CoSAI Workstream 4, Secure Design Patterns for Agentic Systems☆67Updated last week
- Daily updates from leaked data search engines, aggregators and similar services.☆140Updated this week
- An interactive CLI application for interacting with authenticated Jupyter instances.☆55Updated 8 months ago
- A repository for maintaining a list of the top domains based on multiple lists☆23Updated 3 years ago
- Parseltongue 3.1 - LLM Payload Crafter for AI safety research☆51Updated 2 months ago
- PWN is an open security automation framework that aims to stand on the shoulders of security giants, promoting trust and innovation.☆67Updated 2 weeks ago
- LLM | Security | Operations in one github repo with good links and pictures.☆86Updated last week
- Import, visualize, and analyze SpiderFoot scans in Neo4j, a graph database☆80Updated 3 years ago
- ☆14Updated last year
- Autonomous AI C2☆33Updated last year
- A collection of prompt injection mitigation techniques.☆26Updated 2 years ago
- SSE to Stdio MCP Proxy Server☆16Updated 7 months ago
- Official code for the paper entitled "Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense"☆15Updated 9 months ago
- Multi-agent system (MAS) hijacking demos☆39Updated this week
- An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for autho…☆26Updated 2 months ago
- Static code analyser for backdoors and malicious code in git repos using OpenAI compatible LLM APIs☆73Updated last year
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆83Updated 8 months ago
- a hackbot proof-of-concept☆41Updated last year
- MCP server for dnstwist, a powerful DNS fuzzing tool that helps detect typosquatting, phishing, and corporate espionage.☆41Updated 10 months ago
- ☆29Updated 2 years ago
- 🤖 A GitHub action that leverages fabric patterns through an agent-based approach☆33Updated last year