Open database of system prompts extracted from frontier LLMs using JustAsk
A collection of extracted system prompts/operational instructions
Reverse-engineered system prompts from Claude (claude.ai) and Claude Code CLI, validated against Anthropic's officially published prompts.
Source code of the paper "Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models"
Official implementation of "ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks"
Explore and compare 45+ system prompts across models with a live gallery, research paper, and open dataset for prompt analysis
colony-probe is a defensive prompt-confidentiality audit tool that tests whether a deployment leaks its hidden system prompt through ordinary-looking multi-turn questions. It runs a multi-turn probe of individually innocuous queries and estimates how much of the system prompt can be reconstructed from the answers. Authorized defensive use only.
Add a description, image, and links to the prompt-extraction topic page so that developers can more easily learn about it.
To associate your repository with the prompt-extraction topic, visit your repo's landing page and select "manage topics."