Codex 现可为每个 GitHub PR 执行安全审查并内联评论
OpenAI 给 Codex 加了自动安全审查能力，直接在每个 GitHub PR 上挑毛病并写评论，团队不用手动盯代码了。
OpenAI 推出 Codex Security Review 研究预览版。该功能会自动审查 GitHub 拉取请求中的安全漏洞，并利用仓库上下文直接在 PR 中给出可操作的修改建议。
开发者可通过 learn.chatgpt.
com/docs/security 文档启用自动审查。OpenAI 表示这是提升代码与公司整体安全性的计划之一。
Codex can now perform a security review of every GitHub pull request, leaving findings inline. Part of an overall initiative to help apply these models to increase the security of code and companies everywhere: OpenAI Developers @OpenAIDevs Now in research preview: Codex Security Review It takes a deeper look at GitHub pull requests for security issues, using repository context to surface actionable findings directly in the PR. See how to enable automatic reviews: learn.chatgpt.com/docs/security/…
This report is categorized under AITOP's "Products" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Codex, GitHub, OpenAI, AI安全.
Source attribution: curated from Greg Brockman (@gdb). Cross-source corroboration: 11 independent sources have covered this development (including @OpenAIDevs, Latent.Space, IT之家), confirming industry-wide signal strength.
