Skip to content
Agentic Problems and the Rise of Zombie AIs
ethiack.com | research | #ai-security | #prompt-injection | #llm-security | #ai-agents | #chatgpt | #ethiack | #hackaicon
Summary
Johann Rehberger shares HackAIcon research on hijacking AI agents: ChatGPT Operator was manipulated via prompt injection and a fake tool into leaking private data, despite multiple OpenAI defenses.
- Published
- Collected