# OpenAI Warns AI Agents May ALWAYS Face Prompt Injection Attacks

An episode of [AI Chat: AI News on Claude, ChatGPT, Gemini, Grok, Perplexity](https://invisiblenetwork.ai/podcast/1669990482), 28 Dec 2025, 15 min.

Audio: https://content.rss.com/episodes/365073/2440630/ai-chat-podcast/2026_01_08_18_55_58_7118303c-e557-4221-9d90-187cbcea87f0.mp3

Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode! In this episode, we break down why OpenAI says AI-powered browsers may always be vulnerable to prompt injection attacks. We explain what prompt injection is, why it’s so difficult to fully prevent, and what this means for the future of AI agents on the web. • Try Delve: https://delve.co/ • Get the top 40+ AI Models for $20 at AI Box: https://aibox.ai • Join my AI Hustle Community: https://www.skool.com/aihustle - See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Shows are listed from Apple Podcasts' charts and directory, and Podcast Index where it is used. Every show and episode belongs to its publisher and plays from the publisher's own feed; this site hosts none of them.