P
PromptInject
agencyenterprise/PromptInject
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022
★515stars
Python
MIT
Updated: 4d ago
📋 Project at a Glance
Tap to expand
What's this?A adversarial-attacks/agi tool in the Security & Governance category, built with Python, open-source
Who made it?Maintained by agencyenterprise team, 515⭐ on GitHub, #193 out of 413 in Security & Governance
Why does it exist?With the growing demand for adversarial-attacks and agi in Security & Governance, agencyenterprise created PromptInject as a streamlined solution.
What can it do?Key use cases: agi-alignment, ai-alignment, ai-safety
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/agencyenterprise/PromptInject
🔗 github.com/agencyenterprise/PromptInject
Topics
adversarial-attacksagiagi-alignmentai-alignmentai-safetychain-of-thoughtgpt-3language-modelslarge-language-modelsmachine-learningml-safetyprompt-engineering