Tag
Josh Rosen outlines emerging architectural patterns for the 'agentic security stack' as software development becomes fully agentic — securing the agent worker itself, frontier labs building security agents (OpenAI Codex Security, Claude Code), and vendors embedding security directly into coding-agent loops via MCP, hooks, and skills.
OpenAI introduces Codex Security, an agentic application security tool now in research preview that identifies complex vulnerabilities with high confidence and actionable fixes while significantly reducing false positives and noise compared to traditional security tools.