| ★ |  I Left an AI Hacker Alone for 1 Hour and This Happened… | Cybersecurity Lab Idea | Meera Tamboli @meeratamboli | 4.5K | Reino Unido | |
| 15 |  Cyber Security Expert: “We Don’t Know What Happens When You Link a Million AI Bots” | Shawn Ryan Clips @shawnryanclips | 635.3K | Estados Unidos | 87 |
| 18 |  OpenClaw: The Most Dangerous AI Project on GitHub? | | 315.0K | Estados Unidos | 87 |
| 8 |  I was hacked... | Matthew Berman @matthew_berman | 122.1K | Estados Unidos | 88 |
| 5 |  The Hilariously Easy AI Jailbreak (No Coding Required) | | 108.3K | Estados Unidos | 88 |
| 20 |  Your iPhone Was Hacked Without You Clicking Anything! | | 97.0K | Estados Unidos | 87 |
| 1 |  I built an AI that watches everything… this wasn't supposed to work | | 50.5K | — | 89 |
| 7 |  5 Claude Hacks So Powerful They Should Be Illegal | | 32.0K | — | 88 |
| 3 |  I Tested an AI Hacker | | 17.6K | — | 88 |
| 12 |  Agentic AI Security, Simply Explained (FREE Masterclass) | UnixGuy | Cyber Security @unixguy | 14.0K | Australia | 87 |
| 2 |  I Hacked A Website With ONE Command | Privacy Matters @privacymatters517 | 12.8K | Noruega | 89 |
| 4 |  Ethical Hacking with AI for Absolute Beginners (Full Demo) | AI-Powered Pentesting 2025 | Meera Tamboli @meeratamboli | 10.0K | Reino Unido | 88 |
| 9 |  legally hack AI in 13 minutes | | 10.0K | — | 88 |
| 10 |  HACKERS Are Using This AI Tool | | 9.2K | — | 88 |
| 14 |  I never touched the keyboard. My agents shipped this. | ICOR with Tom | AI Productivity @myicor | 5.2K | Alemania | 87 |
| 13 |  AI Browsers Are Stealing Your Data (Prompt Injection Explained) | | 1.5K | Estados Unidos | 87 |
| 17 |  Rogue Agents Roamed The Open Web For Days And OpenAI Knew (Allegedly) | Tech Coach Ralph @techcoachralph | 126 | Estados Unidos | 87 |
| 19 |  Turbocharge AI with Cloud Code: Agents and Tools | Sebastian Hardy @coachsebhardy | 39 | Estados Unidos | 87 |
| 11 |  How To Hack AI (Exploiting LLM APIs with excessive agency) | | 37 | — | 87 |
| 6 |  How To Hack AI (Exploiting insecure output handling in LLMs) | | 36 | — | 88 |
| 16 |  How To Hack AI (Indirect prompt injection) | | 15 | — | 87 |