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 skills add zhizhuodemao/ai-reverse-toolkit --skill find-crypto-entrygit clone --depth 1 https://github.com/zhizhuodemao/ai-reverse-toolkitWrote 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/zhizhuodemao/ai-reverse-toolkit/find-crypto-entry)<a href="https://agentmods.dev/skills/zhizhuodemao/ai-reverse-toolkit/find-crypto-entry"><img src="https://agentmods.dev/badge/skills/zhizhuodemao/ai-reverse-toolkit/find-crypto-entry/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.
<a href="https://agentmods.dev/skills/zhizhuodemao/ai-reverse-toolkit/find-crypto-entry"><img src="https://agentmods.dev/badge/skills/zhizhuodemao/ai-reverse-toolkit/find-crypto-entry.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.00973 |
| Opus 5 | $0.00010 | $0.00487 |
| Sonnet 5 | $0.00004 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
find-crypto-entry 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 11d 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.
What it actually says
find-crypto-entry
定位加密参数 $ARGUMENTS 的生成入口。
目标:找到生成该参数的函数位置(脚本 URL + 行列号 + 函数名 + 调用路径)。
策略选择
根据信号选择策略,不要按固定顺序执行:
优先静态搜索:用 search_in_sources 搜参数名(带 excludeMinified=false)。大多数情况下直接找到赋值位置,然后读上下文追溯来源。
静态搜不到时用 XHR 断点:break_on_xhr 设在请求 URL 特征上,刷新页面触发。断点命中后从调用栈中找业务代码帧,用 evaluate_on_callframe 检查变量。
两种策略可以组合:先静态搜索定位赋值位置,再在赋值处设断点动态验证。
领域知识
agent 在逆向分析中容易踩的坑,这些是无法通过推理得出的经验:
加密参数的 3 种常见架构
- 业务代码直接赋值 — 在请求函数中
headers["x-sign"] = encrypt(data)。静态搜索直接找到。 - 请求拦截器统一加签 — axios interceptor 或 fetch wrapper 中统一添加。搜参数名可能只在拦截器中出现一次。
- 外部安全 SDK — 独立 JS 文件(通常混淆)挂载全局对象(如
window.h5sign),业务代码调用其方法。静态搜索能找到调用处,但 SDK 内部代码全被混淆。
OB 混淆的影响
当加密逻辑在 OB 混淆的文件中(特征:_0x 前缀、大型字符串数组、RC4 解密函数),所有字符串都被加密,静态搜索在该文件内无法匹配任何明文。但调用该文件的业务代码通常未混淆,从业务代码侧搜索更高效。
XHR 断点命中时的堆栈特点
XHR 断点命中在 send() 调用处,调用栈底部通常是框架代码(axios/fetch wrapper)。加密逻辑在栈的中上层。直接跳过底部框架帧,关注业务代码帧。
反模式
- 不要反复 step_into — 容易掉进框架响应式系统(Vue reactivity、React fiber)。用
evaluate_on_callframe直接检查变量比单步跟踪高效得多。 - 不要在 OB 混淆文件中搜字符串 — 所有明文都被加密了,搜不到。从非混淆的调用方搜。
- 不要频繁刷新页面 — 每次刷新所有 scriptId 失效。设好断点再刷新,一次到位。
- 断点命中时优先用
evaluate_on_callframe指定帧 —evaluate_script在暂停时会自动 fallback 到顶层帧,但如果需要检查特定调用帧的变量,必须用evaluate_on_callframe指定frameIndex。
完成标准
找到以下信息即为完成:
入口位置:
- 参数:$ARGUMENTS
- 脚本:https://example.com/static/js/main.abc123.js
- 位置:第 X 行,第 Y 列
- 函数:functionName (或 anonymous)
- 调用路径:request → addSign → encrypt
- 加密类型:[标准算法名 | 外部SDK | 未知/需解混淆]
只找入口,不做算法还原。
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.
- 11d ago First seen · 73 lines · 0 tokens per session scan A 056f8dab8808
find-crypto-entry is a skill published in the GitHub repository zhizhuodemao/ai-reverse-toolkit (440 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 973 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…