ToolsThe story, in brief
Codex Security: now in research preview
OpenAI ships Codex Security: AI agents that find and patch vulnerabilities autonomously.
The KeyNews take
Why it matters
OpenAI is moving beyond chat into enterprise security workflows. Codex Security represents the shift from model-as-tool to autonomous agent-as-product—reducing security team friction and potentially reshaping how enterprises approach vulnerability management.
The key facts
5 to knowOpenAI launches Codex Security in research preview
Application: AI-driven application security agent
Core capability: detect, validate, and patch vulnerabilities with reduced false positives
Target use case: complex vulnerability analysis with project context awareness
Status: research preview (early availability, not general release)
Go to the source
OpenAI Blogopenai.com
Publisher excerpt: Codex Security is an AI application security agent that analyzes project context to detect, validate, and patch complex vulnerabilities with higher confidence and less noise.