— Topic

Atlas Browser

2 briefings

OpenAI Discloses Persistent Security Risks in Atlas Browser as 'Prompt Injection' Battles Escalate

Following reports of critical vulnerabilities by LayerX, OpenAI admits that securing AI browsers against indirect prompt injection is an ongoing arms race, raising concerns for user privacy and enterprise adoption.

Dec 27, 2025 3 min read

OpenAI

OpenAI Hardens Atlas Browser Security as Prompt Injection Threats Persist

As OpenAI rolls out new defenses for its agentic browser, the company admits that prompt injection attacks may be an indefinite vulnerability for AI systems.

Dec 26, 2025 4 min read