Want to deploy AI in your cloud apps SAFELY? Let Wiz help: https://ntck.co/wiz
Can you hack AI? In this video I sit down with elite AI hacker Jason Haddix to unpack how attackers compromise AI-enabled appsânot just jailbreak chatbots, but exfiltrate customer data, abuse tool calls, and pivot across systems. We walk through his six-part AI pentest blueprint, play the Gandalf prompt-injection game, and demo wild techniques like emoji smuggling and link smuggling. Youâll see real-world 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: web-layer fundamentals, a âfirewall for AIâ on inputs/outputs, and least-privilege for data and toolsâplus a hands-on demo you can try. If youâre building with AI in 2025, this is your wake-up call (and your roadmap). Educational content onlyâhack ethically and only with permission.
đ Watch the Full Interview here: https://youtu.be/2Z-9EOyb6HE
Links and STUFF
â——————————————————–
Practice Prompt Injection: https://gandalf.lakera.ai/baseline
Pliney's Github: https://github.com/elder-plinius
Follow Jason Everywhere:
X: https://x.com/Jhaddix
Linkedin: https://www.linkedin.com/in/jhaddix/
Instagram: https://www.instagram.com/j.haddix56/
Tiktok: https://www.tiktok.com/@jhaddix56
Checkout Jasonâs courses:
Website: https://www.arcanum-sec.com/
Training Overview: Training: https://www.arcanum-sec.com/training-overview
Attacking AI course: https://www.arcanum-sec.com/training/attacking-ai
Hacking your career: https://www.arcanum-sec.com/training/hack-your-brand
đĽđĽJoin the NetworkChuck Academy!: https://ntck.co/NCAcademy
**Sponsored by Wiz.io
00:00 – Hack companies through AI?
00:58 – What does âhacking AIâ really mean?
01:43 – AI pentest vs. red teaming (6-step blueprint)
02:42 – Prompt Injection 101 (why itâs so hard)
04:14 – Try it live: Gandalf prompt-injection game
05:09 – Jailbreak taxonomy: intents, techniques, evasions
05:55 – Emoji smuggling + anti-classifier demo
07:23 – Link smuggling (data exfiltration trick)
11:38 – Real-world leaks: Salesforce/Slack bot case
13:47 – MCP security risks u0026 blast radius
16:55 – Can AI hack for us? Agents u0026 bug bounties
20:52 – Defense in depth: web, AI firewall, least privilege
24:57 – Jasonâs Magic Card: GPT-4o system prompt leak (wild story)
SUPPORT NETWORKCHUCK
—————————————————
âĄď¸NetworkChuck membership: https://ntck.co/Premium
ââ COFFEE and MERCH: https://ntck.co/coffee
Check out my new channel: https://ntck.co/ncclips
đđNEED HELP?? Join the Discord Server: https://discord.gg/networkchuck
STUDY WITH ME on Twitch: https://bit.ly/nc_twitch
READY TO LEARN??
—————————————————
-Learn Python: https://bit.ly/3rzZjzz
-Get your CCNA: https://bit.ly/nc-ccna
FOLLOW ME EVERYWHERE
—————————————————
Instagram: https://www.instagram.com/networkchuck/
Twitter: https://twitter.com/networkchuck
Facebook: https://www.facebook.com/NetworkChuck/
Join the Discord server: http://bit.ly/nc-discord
AFFILIATES u0026 REFERRALS
—————————————————
(GEAR I USE…STUFF I RECOMMEND)
My network gear: https://geni.us/L6wyIUj
Amazon Affiliate Store: https://www.amazon.com/shop/networkchuck
Buy a Raspberry Pi: https://geni.us/aBeqAL
Do you want to know how I draw on the screen?? Go to https://ntck.co/EpicPen and use code NetworkChuck to get 20% off!!
fast and reliable unifi in the cloud: https://hostifi.com/?via=chuck
Prompt Injection explained with live demos: Gandalf game, emoji smuggling, and link smuggling exfiltration.
AI Pentesting vs AI Red Teaming: a six-phase methodology for securing LLM apps end-to-end.
LLM jailbreak taxonomy: intents, techniques, evasions, and utilitiesâhow attackers actually think.
RAG poisoning, tool-call abuse, and over-scoped API keys: the hidden risks in modern AI products.
MCP (Model Context Protocol) security: tools/resources/prompts, server hardening, and blast-radius control.
Agentic frameworks (LangChain, LangGraph, CrewAI) security pitfallsâand how to test them safely.
Real-world case study: Slack salesbot + Salesforce data exposure and what went wrong.
Defense in depth for AI: input/output validation, a firewall for AI (guardrails/classifiers), least privilege.
Bug bounty + AI: why mid-tier vulns are getting automated while human creativity still wins.
2025 AI security blueprint: map your attack surface, prevent system-prompt leaks, and lock down data access.
#promptinjection #aihacking #airedteaming
