Prompt Injection
## 🛡️ Prompt Injection
Resources focused on exploiting or defending against prompt injections.
- 🌟 | [AnthenaMatrix](https://github.com/AnthenaMatrix) - Comprehensive repository on prompt injection techniques.
- 🔥 | [utkusen/promptmap](https://github.com/utkusen/promptmap) - Tool for mapping and analyzing prompt injections.
- 🔥 | [microsoft/promptbench](https://github.com/microsoft/promptbench) - Benchmarking tool for prompt injection vulnerabilities.
- [Cranot/chatbot-injections-exploits](https://github.com/Cranot/chatbot-injections-exploits) - Repository of exploits based on prompt injections in chatbots.
- [FonduAI/awesome-prompt-injection](https://github.com/FonduAI/awesome-prompt-injection) - Awesome list of resources on prompt injection.
- [TakSec/Prompt-Injection-Everywhere](https://github.com/TakSec/Prompt-Injection-Everywhere) - Guide to prompt injection in various systems.
- [yunwei37/prompt-hacker-collections](https://github.com/yunwei37/prompt-hacker-collections) - Collection of prompt hacking methods and exploits.
- [AdverserialAttack-InjectionPrompt](https://github.com/Moaad-Ben/AdverserialAttack-InjectionPrompt) - Adversarial attacks through prompt injections.when to use it
Community prompt sourced from the open-source GitHub repo TrustAI-laboratory/Learn-Prompt-Hacking (MIT). A "Prompt Injection" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
roleplaycommunitygeneral
source
TrustAI-laboratory/Learn-Prompt-Hacking · MIT