OpenAI says AI browsers may always be vulnerable to prompt injection attacks

Businessghana • December 29, 2025

Share: View original

Even as OpenAI works to harden its Atlas AI browser against cyberattacks, the company admits that prompt injections, a type of attack that...

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

OpenAI's Atlas AI Browser Vulnerable to Prompt Injection Attacks OpenAI has acknowledged that its Atlas AI browser may always be susceptible to prompt injection attacks. Despite ongoing efforts to enhance security against cyber threats, the company admits that these types of vulnerabilities could persist. 2 sources 24

Extracted Entities

Attack Types (1)

Prompt Injection

Platforms (1)

Atlas AI Browser