Yet another research breaks the hype bubble for AI browsers serving serious security flaws

Researchers tested seven popular AI browsers and found four vulnerable to attacks that trick the AI agent into handing over personal data.

Opera’s latest update turns it into an autonomous browsing agent for ChatGPT and Claude

Opera’s new MCP Connector turns Neon into an autonomous browsing agent, letting AI tools like ChatGPT and Claude directly control your browser and complete tasks across websites.

Your AI browser can be hijacked by prompt injection, OpenAI just patched Atlas

OpenAI says it has patched ChatGPT Atlas after internal red teaming found new prompt injection attacks that can hijack AI browser agents. The update adds an adversarially trained model plus stronger safeguards.
The post Your AI browser can be hijacked …