AI Browsers Under Fire: Hidden Web Prompts Can Hijack Your Agent and Connected Accounts

Safety researchers are warning that synthetic intelligence (AI)-powered browsers and brokers from Perplexity, OpenAI, and Anthropic face escalating dangers of covert immediate injection assaults and privateness breaches, doubtlessly exposing consumer knowledge via related accounts and APIs. AI Browser Vulnerabilities Elevate Safety Considerations AI browsers and brokers from Perplexity, OpenAI, and Anthropic are redefining how customers […]



Source link