OpenAI says AI browsers may always be vulnerable to prompt...

Compartió un vínculo

2025-12-22 23:01:52

OpenAI says AI browsers may always be vulnerable to prompt injection attacks

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.'

0 Commentarios 0 Acciones 26 Views