OpenAI released an open-source command-line interface and TypeScript SDK for finding, validating, and patching vulnerabilities in software repositories, according to RuntimeWire and the Codex Security GitHub repository. The Apache-2.0-licensed package scans repositories or Git diffs, preserves scan history, and integrates into continuous-integration pipelines. The release extends Codex into security workflows used by coding agents.
Topics #
Sources #
- Official
[Read article](https://github.com/openai/codex-security) - Press
[RuntimeWire](https://runtimewire.com/article/openai-open-sources-codex-security-cli-typescript-sdk)
Go deeper #
This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.
source & further reading
getreadyforagents.com — original article
Gartner finds enterprise AI inference spending now exceeds model training costs
Enterprise CIOs report unpredictable costs from usage-based AI token billing
Salesforce reports enterprise agentic AI adoption tripled in 2026 with measurable ROI