Impact

Research, security discoveries, and contributions to the field.

Only the most influential work is disclosed here.

Research

The Hidden Dangers of Browsing AI Agents

A comprehensive security evaluation of browsing AI agents, focusing on systemic vulnerabilities across multiple architectural layers. This work presents the first end-to-end threat model for browsing agents and provides actionable guidance for securing their deployment in real-world environments.

Security Discoveries

CVE-2025-62608

Apple MLX

CVE-2025-62609

Apple MLX

CVE-2025-47241

Browser Use