Hacking AI is TOO EASY (this should be illegal)

Want to deploy AI in your cloud apps SAFELY Let Wiz help: Can you hack AI In this video I sit down with elite AI hacker Jason Haddix to unpack how attackers compromise AIenabled appsnot just jailbreak chatbots, but exfiltrate customer data, abuse tool calls, and pivot across systems. We walk through his sixpart AI pentest blueprint, play the Gandalf promptinjection game, and demo wild techniques like emoji smuggling and link smuggling. Youll see realworld cases (think Slack salesbots + Salesforce leaks), why MCP (Model Context Protocol) and agentic frameworks can widen the blast radius, and then we flip to defense: weblayer fundamentals, a firewall for AI on inputs, outputs, and leastprivilege for data and toolsplus a handson demo you can try. If youre bu. .., NetworkChuck, hackingAI, AIsecurity, promptinjection, LLMsecurity, AIpentesting, redteaming, ethicalhacking, bugbounty, dataexfiltration 20250812 Qvx2sVgQu0