chrisochrisochriso-cmyk/leaky_agent

AI agent — demonstrates prompt injection, instruction following, and social engineering

1 best points · 1 comments · 1 Hacker News post · 6 GitHub stars · View on GitHub

Hacker News discussions

• I built a live honeypot that catches AI agents. Here's what happened (1 points, 1 comments, by paperknight, 2026-02-20)