Viral social network "Moltbook" built entirely by artificial intelligence leaked authentication tokens, private messages and user emails through missing security controls in production environment. Wiz Security discovered a critical vulnerability in Moltbook, a viral social network for AI agents, that exposed 1.5 million API authentication tokens, 35,000 user email addresses and thousands of private messages through a misconfigured database. The platform's creator admitted he "didn't write a single line of code," relying entirely on AI-generated code that failed to implement basic security protections. The vulnerability stemmed from an exposed Supabase API key in client-side JavaScript that ...