RetroFed Forum
Your home away from modern life.
OpenAI says AI browsers may always be vulnerable to prompt injection attacks
Post Reply
AuthorMessage
yoasif fedia.io yoasif@fedia.io
Joined: 2023-06-12
Quote

OpenAI says prompt injections will always be a risk for AI browsers with agentic capabilities, like Atlas. But the firm is beefing up its cybersecurity with an "LLM-based automated attacker."

1   Original
Post Reply
Back to top