pi-codex-security - A pi package that brings OpenAI Codex Security int

项目说明

pi-codex-security

A pi package that brings OpenAI Codex Security into your agent sessions: scan repositories for , review se findings, and fix them — all without leaving pi.

What you get

| Piece | Name | What it does |
|-------|------|--------------|
| Tool | security_scan | Runs a Codex Security scan, streams progress, returns a se findings summary plus report/SARIF paths |
| Tool | security_auth_status | Checks Codex Security authentication (ChatGPT sign-in or API key) |
| Command | /security-scan | Ask the agent to scan: /security-scan [path] [--deep] [--diff base[:head]] [--auth mode] |
| Command | /security-status | Show authentication status |
| Skill | codex-security | Teaches the agent scan targeting, result triage, and fix workflows |

Install

Or try it without installing:

Requirements

Run /security-status inside pi to .

Usage

Just ask in natural language:

> Scan this repo for security

> Review my uncommitted changes for security issues

> Fix the critical findings from the last scan

Or use the command for precise control:

The agent calls security_scan, gets back a ranked summary, reads the full report.md, and offers to fix findings highest-se. After fixing, it re-scans to .

security_scan parameters

| Param | Type | Default | Description |
|-------|------|---------|-------------|
| path | string | cwd | Repository or directory to scan |
| mode | standard \| deep | standard | Scan depth |
| auth | auto \| chatgpt \| api-key | auto | Credential selection |
| diffBase | string | — | Scan changes vs this git ref (working tree) |
| diffHead | string | — | With diffBase: scan the base...head ref range |
| minSe | se | low | Minimum se listed indi (counts always co) |
| maxCostUsd | number | — | Abort if estimated cost exceeds this |
| outputDir | string | Codex state dir | Where scan artifacts are written |

Artifacts

Each scan produces:

CI

Set OPENAI_API_KEY and use the Codex Security CLI directly for gating (--fail-on-se, SARIF upload). See the upstream docs. This package is the interacti side of that workflow.

De

Release

Publishing is manual; the tag-dri (.github/workflows/release.yml) the build and creates the GitHub Release:

On the tag push the workflow re-runs typecheck + tests, skips npm publish when the is already on the registry, and creates a GitHub Release with generated notes. If an NPM_TOKEN secret (or npm Trusted Publisher) is configured later, the workflow publishes automatically whenever the tagged isn't on npm yet.

License

MIT

项目信息

开发语言：TypeScript

Star 数：12

技术要点

该项目属于安全软件方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕A pi package that brings OpenAI Codex Security into your agent sessions: scan repositories for vulnerabilities, review severity-ranked findings, and fix them — all without leaving pi.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。