I pulled 50 system prompts from public GitHub repos and tested them for prompt injection vulnerabilities. Average score: 3.7/100. 70% had zero defenses. The best score was 28/100. Here's the full breakdown by attack category.
Dev.to AI
•
Generative AI
AI Tools
I Tested 50 AI App Prompts for Injection Attacks. 90% Scored CRITICAL. Andrei ・ Mar 16