Codex Security 0.2.0 Can Save Threat Models and Adds Credential Leak Scanning

Summary

Codex Security 0.2.0 was released on October 7, 2026, adding threat model persistence for Standard, Deep and Diff scans. Threat models can now be saved alongside scan results and security policies as reusable artifacts, and existing models can be exported directly with the export command without re…

Key points

Threat models become saveable, reusable assets, turning security scanning from a one-off check into an auditable, comparable ongoing process.
Saving threat models alongside scan results lets AI security tool outputs be traced and reviewed, bringing them closer to enterprise compliance and audit needs.
Development teams can integrate offline credential scanning into CI pipelines and use explicit model and effort settings to control patch generation costs, avoiding uncapped inference spending.

AI Tools Weekly

Editorial note

This page is Code & Chain's editorial summary of public sources. It may be prepared with AI assistance and published through an automated workflow. Refer to the original sources; this content is not investment, legal, or tax advice.