In late July 2026 OpenAI released its Codex Security CLI and SDK as open source under Apache 2.0 (npm install @openai/codex-security). It scans repositories, reviews staged and unstaged changes before a commit, and runs in CI with a severity threshold that fails the build on findings at or above a set level. The catch: the underlying scanner stays proprietary and gated to approved beta customers.
Home › Founders News › Tools & AI
OpenAI open-sources Codex Security CLI for pre-merge vulnerability scanning
Why this matters for founders
Lean teams can wire automated vulnerability scanning into their commit and CI flow to catch security issues before merge, though production use still requires OpenAI beta access to the backend scanner.
Source: DevOps.com
Get briefs like this tuned to your business.
In the app, Founder Briefs are personalized to your country, industry and stage, and you can save the ones that matter.
Related updates
More that helps you.
Anthropic ships Claude Opus 5 — near-top-tier performance at half the price
On July 24, 2026 Anthropic released Claude Opus 5, its fourth new model in under 60 days (after Sonnet 5, Fable 5 and Mythos 5 in June). Opus 5 delivers close to flagship Fable 5 q…
OpenAI launches GPT-5.6 family (Sol, Terra, Luna) with big efficiency gains
On July 9, 2026 OpenAI unveiled GPT-5.6 in three variants: Sol (the workhorse), Terra (mid-tier), and Luna (budget). Sam Altman says the models are markedly more token-efficient —…
Moonshot releases Kimi K3, the largest open-weight AI model to date
Moonshot AI released open weights for Kimi K3 on July 27, 2026: a 2.8-trillion-parameter mixture-of-experts model with a 1-million-token context window, the largest open-weight mod…
xAI ships Grok 4.5, an 'Opus-class' coding model at $2/$6 per M tokens
xAI released Grok 4.5 on July 8, 2026, priced at $2 per million input tokens and $6 per million output tokens, with public access the next day. Elon Musk called it 'an Opus-class m…
Keep exploring
Related across the site
Case studyEric YuanZoomCase studyJensen HuangNVIDIACase studyTobias LütkeShopifyToolClaudeClaude is a conversational AI assistant that can write, edit, summarize, analyze documents, code, and reason through problems. It works via chat, and Claude Code brings the same model into a developer terminal.TermMVP (Minimum Viable Product)The simplest version of your product that delivers core value and lets you test key assumptions with real users.AI advisorInnovator EddieInnovation & rapid prototyping