| ★ |  39C3 - A Quick Stop at the HostileShop | | 4.1K | Alemania | |
| 8 |  I Jailbroke an AI to Do Anything I Say | | — | — | 87 |
| 2 |  The Hilariously Easy AI Jailbreak (No Coding Required) | | 108.3K | Estados Unidos | 87 |
| 7 |  Stop Using Restricted AI. Build This Instead. | | 73.3K | — | 87 |
| 17 |  You Need to Learn MCP RIGHT NOW | | 45.1K | — | 86 |
| 3 |  What Is LLM Poisoning? Interesting Break Through | | 32.2K | India | 87 |
| 16 |  Prompt Injection in AI | Data Engineering @dataengineeringtamil | 12.6K | India | 86 |
| 10 |  legally hack AI in 13 minutes | | 10.0K | — | 87 |
| 6 |  HACKERS Are Using This AI Tool | | 9.2K | — | 87 |
| 18 |  DEF CON 33 - Can't Stop the ROP: Automating Universal ASLR Bypasses - Bramwell Brizendine | DEFCONConference @defconconference | 4.8K | Estados Unidos | 86 |
| 4 |  Hacking AI without code | What's AI by Louis-François Bouchard @whatsai | 1.0K | Canadá | 87 |
| 9 |  ⚠️MIRA COMO HACKEO ESTE LLM. PROMPT INJECTION⚠️ | WraithVector | Automatización & IA @wraithvector | 686 | — | 87 |
| 20 |  PROMPT INJECTION 2026 — The LLM Killer Attack Explained | NepHack | | 379 | Australia | 86 |
| 11 |  Lightning Talk: Alcoholless: Lightweight Security Sandbox for Homebrew, AI Agents, E... Akihiro Suda | The Linux Foundation @linuxfoundationorg | 143 | Estados Unidos | 86 |
| 13 |  PROMPT INJECTION. HACKEA A LA IA | WraithVector | Automatización & IA @wraithvector | 76 | — | 86 |
| 5 |  How To Hack AI (Exploiting LLM APIs with excessive agency) | | 37 | — | 87 |
| 1 |  How To Hack AI (Exploiting insecure output handling in LLMs) | | 36 | — | 87 |
| 12 |  Building AI-Powered Security for AI Chatbots | | 33 | — | 86 |
| 19 |  How To Hack AI (Exploiting vulnerabilities in LLM APIs) | | 25 | — | 86 |
| 14 |  Building SentriGuard AI – A Modular AI Safety Gateway (Hackathon Submission) | | 16 | — | 86 |
| 15 |  Securing ChatGPT & LLMs in AWS: Your Ultimate Guide | CyberShield Simplified @cybershieldsimplified | 5 | Estados Unidos | 86 |