Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/zhaji2333/ckskills/miniprogram-securitynpx skills add zhaji2333/CkSKILLS --skill miniprogram-securitygit clone --depth 1 https://github.com/zhaji2333/CkSKILLSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhaji2333/ckskills/miniprogram-security)<a href="https://agentmods.dev/skills/zhaji2333/ckskills/miniprogram-security"><img src="https://agentmods.dev/badge/skills/zhaji2333/ckskills/miniprogram-security.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00160 | $0.03232 |
| Opus 5 | $0.00080 | $0.01616 |
| Sonnet 5 | $0.00032 | $0.00646 |
| Haiku 4.5 | $0.00016 | $0.00323 |
Grade A, and why
miniprogram-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
miniprogram-security — 小程序专项深度挖掘
与
android-security-audit的分工:本技能专注 小程序(微信/支付宝/抖音/百度)与微信云开发;Android APK 组件安全见android-security-audit。小程序与 APP 后台接口常同源,两技能可联动:先从 APP/小程序提取后端域名,再统一测接口。
何时调用(触发条件)
- 目标是微信/支付宝/抖音/百度/QQ 小程序
- 拿到小程序包(.wxapkg / 分包 / 反编译产物),需要还原源码
- 需要提取接口清单、appid/appsecret、云开发配置、加密/签名逻辑
- 发现微信登录链(wx.login code)、支付、openid/用户 ID 可控、未授权接口
- 发现 web-view / rich-text / JSBridge / 分享跳转 等前端渲染点
- 目标是微信云开发(云函数/云数据库/云存储)
快速开始(5 分钟出第一个接口/凭证)
# Step 1: 定位小程序包(PC 微信缓存目录)
# 微信/WeChat Files/Applet/<appid>/ 下 *.wxapkg(含分包)
# 或开发者工具/手机抓包/第三方平台获取
# Step 2: 反编译
# wxappUnpacker / unveilr / CrackMinApp 解包,得到 app.js、app.json、pages/、utils/、cloudfunctions/
# Step 3: 提取敏感信息与接口(高优先级)
grep -rniE "appid|appsecret|secret|access_key|secret_key|token" <解包目录>/
grep -rEoh "https?://[a-zA-Z0-9._/-]+" <解包目录>/ | sort -u # 后端/业务域名
grep -rn "wx.request|wx.cloud.callFunction|request\(" <解包目录>/ | head -50 # 接口与云函数
# Step 4: 优先验证
# openid 可控 → 替换他人 openid 测越权;登录 code → 重放/替换;支付参数 → 金额篡改
一、包获取与反编译
获取途径
- PC 微信:
WeChat Files/Applet/<appid>/下.wxapkg缓存(主包+分包),需先在小程序里打开过 - 微信开发者工具:导入源码调试(拿到项目源码的场景)
- 手机抓包:HTTP(S) 代理 + 小程序包下载接口(配合证书安装)
- 第三方平台:小程序包下载站、GitHub 泄露、历史版本
- 其他平台:支付宝(.axml)、抖音、百度(.swan)结构类似,解包工具对应适配
反编译工具
wxappUnpacker # 经典解包,还原 app.js/pages 结构
unveilr # 较新,支持分包/新版格式
CrackMinApp # 微信小程序一键解包
- 解包产物结构:
app.js(全局逻辑)、app.json(页面/权限配置)、pages/*(页面)、utils/*、project.config.json、cloudfunctions/(云函数目录) - 新版分包需先解主包再按
app.json的subpackages配置逐分包解 - 压缩混淆的 JS:先用 js-beautify/反混淆还原,再搜索关键字
还原度确认:解包后核对 app.json 页面数与线上功能是否对应,确认还原完整再开始审计。
二、静态审计重点(代码层面)
app.js / 全局逻辑
- 全局接口封装、请求拦截器(看统一鉴权头怎么带的:token?openid?自定义签名?)
- 登录流程:
wx.login()→ code → 后端换 session/token 的完整链路 - 全局变量:appid、环境 env、后台域名、加密密钥
敏感信息(重点上报项,联动 recon-js-analysis)
appid(正常)、appsecret出现在前端 = 配置错误/泄露(后端才应持有)→ 上报并深挖(可换取 access_token 调接口)- 云开发 env ID、腾讯云 SecretId/SecretKey、OSS/存储桶密钥、内网/后台域名
- 提取的 URL/IP/域名 → 提醒用户关注:可能是 APP/小程序后台接口,进入资产测绘
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 199 lines · 160 tokens per session scan A 27cd854f0cb7
miniprogram-security is a skill published in the GitHub repository zhaji2333/CkSKILLS (73 stars, last pushed 3d ago), licensed MIT. It adds 160 tokens to every session and 3,232 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
gpt-image-2
面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用:(A) Garden 本地模式,通过 OpenAI 兼容接口直接出图并落盘;(B) Host-Native 模式,把本 Skill 当作提示词工程指引,把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图;(C) Advisor 模式,宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板,覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.
new
Create a new project to start development quickly.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…