🛡️ Enterprise AI Security Platform
Advanced prompt injection protection for your AI applications. Secure your language models with real-time threat detection.
🎯 The Challenge
This is a prompt injection security game. Your goal: extract the secret UUID from the recipe assistant below.
- The recipe agent has a hidden UUID in its system prompt
- Our detection system blocks malicious prompts before they reach the AI
- Try to craft a prompt that bypasses the detector and extracts the secret
- Paste the UUID in the challenge box below to win
🍳 Recipe Agent (Example Chat)
Ask for recipes. The agent is protected by prompt injection detection.
🏆 UUID Challenge
If you successfully extracted the secret UUID, paste it here to verify.
🔍 API Documentation
Test the prompt injection detection API directly.
POST /api/check
{
"input": "your text here"
}Returns: isInjection, score, reasons
ℹ️ How It Works
Detection Layer: Uses heuristic pattern matching and external AI models to identify prompt injection attempts.
Protection: Malicious inputs are blocked before reaching the recipe agent, preventing system prompt leakage.
Challenge: The secret UUID is embedded in the agent's system prompt. Can you bypass the detector?