OpenAI says AI browsers may always be vulnerable to prompt injection attacks
Dec 22, 2025
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."
https://techcrunch.com/2025/12/22/openai-says-ai-browsers-may-always-be-vulnerable-to-prompt-injection-attacks/
Respond, make new discussions, see other discussions and customize your news...

To add this website to your home screen:

1. Tap tutorialsPoint

2. Select 'Add to Home screen' or 'Install app'.

3. Follow the on-scrren instructions.

Feedback
FAQ
Privacy Policy
Terms of Service