# asgeirtj/system_prompts_leaks

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/asgeirtj-system-prompts-leaks).**

32,149 stars · 5,118 forks · HTML

## Links

- GitHub: https://github.com/asgeirtj/system_prompts_leaks
- awesome-repositories: https://awesome-repositories.com/repository/asgeirtj-system-prompts-leaks.md

## Topics

`ai` `anthropic` `chatbots` `chatgpt` `claude` `gemini` `generative-ai` `google-deepmind` `large-language-models` `llm` `openai` `prompt-engineering` `prompt-injection` `prompts`

## Description

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.

## Tags

### Artificial Intelligence & ML

- [System Prompt Collections](https://awesome-repositories.com/f/artificial-intelligence-ml/system-prompt-collections.md) — Provides a comprehensive directory of system prompts for various AI models. ([source](https://cdn.jsdelivr.net/gh/asgeirtj/system_prompts_leaks@main/README.md))
- [System Prompts](https://awesome-repositories.com/f/artificial-intelligence-ml/system-prompts.md) — | 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 | | ([source](https://cdn.jsdelivr.net/gh/asgeirtj/system_prompts_leaks@main/README.md))
- [Model Behavioral Analysis](https://awesome-repositories.com/f/artificial-intelligence-ml/model-behavioral-analysis.md) — Studying the hidden instructions and behavioral constraints that define how major artificial intelligence models interact with users.
- [Prompt Libraries](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-libraries.md) — Provides a structured directory of system prompts and configurations for various large language model versions. ([source](https://cdn.jsdelivr.net/gh/asgeirtj/system_prompts_leaks@main/README.md))
- [AI Agent Auditing Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-auditing-tools.md) — Analyzes the operational guidelines and safety protocols that govern autonomous coding agents.
- [Model Intelligence Databases](https://awesome-repositories.com/f/artificial-intelligence-ml/model-intelligence-databases.md) — A structured database documenting the internal directives and operational constraints that define the personality and functional boundaries of artificial intelligence agents.
- [Prompt Engineering Techniques](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-engineering-techniques.md) — Refines custom instructions by observing proven techniques used by industry-leading AI products.

### Security & Cryptography

- [AI Security Research](https://awesome-repositories.com/f/security-cryptography/ai-security-research.md) — Investigates potential vulnerabilities and information disclosure risks within proprietary model configurations.

### Testing & Quality Assurance

- [Model Evaluation](https://awesome-repositories.com/f/testing-quality-assurance/model-testing/model-evaluation.md) — Provides curated configuration data to analyze model alignment and safety guardrails.

### Data & Databases

- [Crowdsourced Data Aggregators](https://awesome-repositories.com/f/data-databases/crowdsourced-data-aggregators.md) — Collects and organizes structured information from distributed contributors into a centralized repository for public analysis.