asgeirtj/system_prompts_leaks
System Prompts Leaks
This project is a centralized repository for the collection and analysis of system instructions and behavioral configurations extracted from large language models and AI-powered software. It serves as a research archive that documents the internal directives, operational constraints, and safety protocols that define how various artificial intelligence agents interact with users.
The repository distinguishes itself through a crowdsourced approach to data aggregation, maintaining a historical record of configuration changes across a wide range of proprietary models and coding assistants. By organizing these findings into structured, version-controlled datasets, it enables security researchers and developers to audit model alignment, investigate potential information disclosure risks, and observe the structural patterns used in production-grade prompt engineering.
The project covers a broad capability surface, including the study of hidden behavioral constraints and the auditing of autonomous agent guidelines. It utilizes standardized, human-readable tabular storage to ensure that the collected data remains accessible for comparative analysis. The entire dataset is presented through a searchable, static web interface that tracks updates and modifications over time.
Features
- System Prompt Collections - Provides a comprehensive directory of system prompts for various AI models.
- System Prompts - | Model | Prompt | |-------|--------| | Gemini 3.5 Flash | System prompt · AI Studio · Tools | | Gemini 3.1 Pro | System prompt · API | | Gemini CLI | System prompt | | Antigravity CLI | System prompt | |
- Model Behavioral Analysis - Studying the hidden instructions and behavioral constraints that define how major artificial intelligence models interact with users.
- Prompt Libraries - Provides a structured directory of system prompts and configurations for various large language model versions.
- AI Security Research - Investigates potential vulnerabilities and information disclosure risks within proprietary model configurations.
- AI Agent Auditing Tools - Analyzes the operational guidelines and safety protocols that govern autonomous coding agents.
- Model Evaluation - Provides curated configuration data to analyze model alignment and safety guardrails.
- Model Intelligence Databases - A structured database documenting the internal directives and operational constraints that define the personality and functional boundaries of artificial intelligence agents.
- Prompt Engineering Techniques - Refines custom instructions by observing proven techniques used by industry-leading AI products.
- Crowdsourced Data Aggregators - Collects and organizes structured information from distributed contributors into a centralized repository for public analysis.
