agentmods.dev

gwxapkg-ai-audit

gwxapkg-ai-audit is a skill for Claude Code, Codex from 25smoking/Gwxapkg. It costs 57 tokens per session (2,594 once invoked), scanned A, original, MIT.

A local security-audit workflow for unpacked WeChat Mini Programs, which are small apps that run inside WeChat, using files and scan results as evidence.

In plain words
What is it for?
Use it to review an unpacked Mini Program, optional captured HTTP requests, and generated scan artifacts, then write findings with evidence, limits, and possible fixes.
Why use it?
It helps investigate likely login, access-control, payment, upload, sharing, and web-view risks without treating keyword matches as confirmed vulnerabilities.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

not rated 156repo +2 23d ago A scan SkillSpector: pass 57 tokens original MIT

Good fit Use it to review an unpacked Mini Program, optional captured HTTP requests, and generated scan artifacts, then write findings with evidence, limits, and possible fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/25smoking/gwxapkg/gwxapkg-ai-audit
View source ↗ 25smoking/Gwxapkg
Install

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.

Any agent
npx skills add 25smoking/Gwxapkg --skill gwxapkg-ai-audit
Clone the repo
git clone --depth 1 https://github.com/25smoking/Gwxapkg

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for gwxapkg-ai-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/25smoking/gwxapkg/gwxapkg-ai-audit/github.svg)](https://agentmods.dev/skills/25smoking/gwxapkg/gwxapkg-ai-audit)
Your own site
<a href="https://agentmods.dev/skills/25smoking/gwxapkg/gwxapkg-ai-audit"><img src="https://agentmods.dev/badge/skills/25smoking/gwxapkg/gwxapkg-ai-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gwxapkg-ai-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/25smoking/gwxapkg/gwxapkg-ai-audit"><img src="https://agentmods.dev/badge/skills/25smoking/gwxapkg/gwxapkg-ai-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,594 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02594
Opus 5 $0.00028 $0.01297
Sonnet 5 $0.00011 $0.00519
Haiku 4.5 $0.00006 $0.00259

Measured 12d ago against content hash c09e46e6ec22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gwxapkg-ai-audit 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 12d 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.

skills/gwxapkg-ai-audit/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gwxapkg AI Audit

目标

对已经由 Gwxapkg 解包并执行过 semantic / scan 的微信小程序目录做本地静态安全审计。优先消费确定性产物，再让 LLM 做证据归纳、缺口检查、业务风险解释和报告组织。

核心目标：在以下业务漏洞面上产出更多、更准确的 findings：

  1. auth：登录 / 注册 / 短信验证码 / 重置密码
  2. idor：用户信息、订单、证件/查询类（对象级越权高发）
  3. payment：支付 / 优惠 / 积分
  4. upload / share / webview / plugin：上传、分享、web-view、插件

Gwxapkg 已用确定性规则生成 .gwxapkg/business_surface.* 与 ai_audit 中的业务假设；LLM 负责：回溯源码、补证据、去误报、写清风险边界与修复，而不是从零扫全站关键词。

该 skill 可由 Hermes + GPT-5.5、Codex、Claude Code 等 Agent 使用。

只在授权测试、内部审计、应急分析场景使用。默认不联网、不重放请求、不验证账号密码、不编写利用代码，不修改被审计源码。

可选活体验证（需显式授权）：

gwxapkg validate -dir=<dir> -base-url=https://api.example.com -i-authorize-live=true \
  -token=<登录token> -token-b=<第二账号token可选> -probe-ids=1,2,others
  • 会把 BIZ-* 从 needs_server_validation 更新为 confirmed / false_positive / inconclusive
  • 读取 .gwxapkg/validation_report.json 作为活体证据
  • 默认不发送短信/下单/删除类请求

输入

  • 必需：一个已解包目录，例如 /path/to/output/wxappid。
  • 可选：Burp 原始请求文件或粘贴的 HTTP raw request。
  • 可选：审计重点，例如未授权访问、算法还原、敏感信息、短信验证码、注册登录、证书查询。

快速流程

  1. 校验目录：确认存在 JS/WXML/JSON 文件，优先确认 .gwxapkg/ 目录。
  2. 优先运行 gwxapkg audit -dir=<dir> -fix=true（doctor + 业务面预筛 + findings 骨架）。
  3. 若仍缺 API/扫描产物：gwxapkg semantic -dir=<dir> / gwxapkg scan-only -dir=<dir> -format=both。
  4. 先读业务面，再读 API/敏感信息；不要一上来全量读源码。
  5. 按 auth → idor → payment → upload/share/webview/plugin 推进假设。
  6. 对每条业务假设回溯源码，补证据行号与参数流；做覆盖缺口检查。
  7. 去重、定级、写清 needs_server_validation 边界；续写 ai_audit/。

优先读取的产物

按顺序读取存在的文件：

  • .gwxapkg/business_surface.json / .md（业务面主入口）
  • .gwxapkg/ai_audit/business_hypotheses.json / business_checklist.md
  • .gwxapkg/ai_audit/findings.json（含 BIZ-* 业务假设）
  • .gwxapkg/doctor_report.json
  • .gwxapkg/api_unified_map.json（含 business_tags 时优先）
  • .gwxapkg/api_map.json / api_endpoint_map.json
  • .gwxapkg/api_call_chain.json / dataflow_hints.json
  • .gwxapkg/semantic_module_map.json / ast_rename_map.json
  • .gwxapkg/burp_api_link.json
  • route_manifest.json
  • sensitive_report.json

Read the full file on GitHub · 182 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 182 lines · 57 tokens per session scan A c09e46e6ec22

Subscribe to this mod's changes

gwxapkg-ai-audit is a skill published in the GitHub repository 25smoking/Gwxapkg (156 stars, last pushed 23d ago), licensed MIT. It adds 57 tokens to every session and 2,594 once invoked, about $0.0003 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.

Security
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens