Dicklesworthstone/acip
The Advanced Cognitive Inoculation Prompt
This project offers a sophisticated set of instructions, called an 'inoculation prompt,' to protect Large Language Models (LLMs) from advanced hacking attempts known as prompt injections. By feeding these instructions into your LLM, you can make it more robust against subtle manipulative prompts. The output is a more secure LLM that adheres to its intended purpose without being tricked. This is for anyone who uses LLMs in their business to handle sensitive tasks or data, such as product managers, security engineers, or operations teams.
300 stars.
Use this if you are deploying a Large Language Model and are concerned about it being manipulated or hijacked by advanced prompt injection attacks, especially when it interacts with external tools or data.
Not ideal if your primary concern is minimizing token usage and latency, as including this prompt increases both, or if you need absolute, guaranteed protection, which no solution can offer.
Stars
300
Forks
25
Language
Shell
License
—
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Dicklesworthstone/acip"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
protectai/llm-guard
The Security Toolkit for LLM Interactions
MaxMLang/pytector
Easy to use LLM Prompt Injection Detection / Detector Python Package with support for local...
utkusen/promptmap
a security scanner for custom LLM applications
agencyenterprise/PromptInject
PromptInject is a framework that assembles prompts in a modular fashion to provide a...
Resk-Security/Resk-LLM
Resk is a robust Python library designed to enhance security and manage context when...