---
title: "this thing is a security nightmare"
url: https://daily.dev/posts/this-thing-is-a-security-nightmare-hmng8j6oa
source_url: https://www.youtube.com/watch?v=Plzp5z5RsJw
type: video:youtube
source: "Low Level Learning"
published: 2025-10-24T17:19:02.655Z
updated: 2025-10-24T17:24:37.779Z
tags: ["ai", "security", "privacy", "prompt-injection"]
reading_time: 10
upvotes: 14
comments: 2
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# this thing is a security nightmare

**[Low Level Learning](https://daily.dev/sources/lowlevellearning)** · 10 min read · 14 upvotes · 2 comments

## Summary

AI-powered browsers like ChatGPT Atlas and Comet pose significant security and privacy risks. These browsers grant AI models access to complete browsing history and habits, creating privacy concerns even when opt-out settings exist. More critically, they're vulnerable to prompt injection attacks where malicious websites can embed hidden instructions that hijack the AI agent controlling the browser, potentially stealing sensitive data like authentication codes. The fundamental flaw is combining an AI system that ingests arbitrary content with browser control capabilities, creating attack vectors that even OpenAI's CEO acknowledges can only be 95% mitigated. Ironically, these AI companies build their browsers by forking Chromium rather than using AI to write code from scratch.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=Plzp5z5RsJw>

## Community discussion

Top comments from developers on daily.dev.

**@isaacmathew** · 1 upvotes

> Just use browsers for AI; and do normal browsing in other browsers. Have different browsers for different states of internet being.

**@surajshetty** · 0 upvotes

> We built AI to protect us from humans. Turns out, it needed protection from websites.

## Similar posts on daily.dev

- [The Problem with AI Browsers: Security Flaws and the End of Privacy](https://daily.dev/posts/the-problem-with-ai-browsers-security-flaws-and-the-end-of-privacy-pdadbrezs) · Towards Data Science · 0 upvotes · 0 comments

---

Tags: [#ai](https://daily.dev/tags/ai), [#security](https://daily.dev/tags/security), [#privacy](https://daily.dev/tags/privacy), [#prompt-injection](https://daily.dev/tags/prompt-injection)

[View this post on daily.dev](https://daily.dev/posts/this-thing-is-a-security-nightmare-hmng8j6oa)