Unverified50% confidenceFactExact time
OpenAI将Codex Security定义为一个'应用安全Agent'，帮助团队发现、确认、修复代码漏洞
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/23/2026
First Seen
Valid until: 11/21/2026
Sources
Related Entities
Related Claims
UnverifiedOpenAI showcased an example of a user discovering a critical vulnerability in Reactor through Codex, marking AI's transition from passive assistance to active discovery in real-world security auditing.79% similarUnverifiedCodex App的技能系统支持通过Secure Install命令从OpenAI官方技能库安装技能79% similarUnverifiedOpenAI 的编程助手 Codex 开始对子代理（sub-agent）的提示词进行加密处理79% similarUnverifiedOpenAI正在推进可信访问计划（Trusted Access Program）用于网络安全74% similarUnverifiedCodex Security有两种形态：一个命令行工具和一个TypeScript SDK，都发布在npm上，包名为@openai/codex-security，采用Apache 2.0许可证73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/789101API
curl https://kongchang.com/api/v1/knowledge/claims/789101MCP
get_claim(id=789101)