diff --git a/tcaptcha/VM_SPEC.md b/tcaptcha/VM_SPEC.md new file mode 100644 index 0000000..3a2a6dc --- /dev/null +++ b/tcaptcha/VM_SPEC.md @@ -0,0 +1,225 @@ +# 腾讯天御 Chaos VM 规范(纯粹从源码/反汇编fact整理) + +> 目的:把 TDC 的 JSVMP(`__TENCENT_CHAOS_VM`)从"读不懂"变成"有确定规格",供纯 Python 复现与静态提取使用。 +> 事实来源:`tcaptcha/core_js/tdc_sample.js` 的 VM 源码(AST 导出)+ `tools/tdc_disasm.py` 的正确反汇编。 +> 工具:`tools/tdc_disasm.py`(提取+CFG 反汇编)、`tools/tdc_vm_run.py`(纯 Python 解释器,WIP)。 + +--- + +## 1. 架构总览 + +VM 就是一个**基于栈的字节码解释器**,入口签名(源码原样): + +```js +function __TENCENT_CHAOS_VM(H, z, c, E, I, D, U, C) { + var g, A = !E, + B = (H = +H, z = z || [0], E = E || [[this], [{}]], I = I || {}, []), + w = null; + function Q() { return function (A, B, w) { return new (Function.bind.apply(A, B))(); }.apply(null, arguments); } + /* ... 定义 58 个 handler,装配成 G 数组 ... */ + for (var G = [ /* handlers */ ], M = !1; !M; ) M = G[z[H++]](); +} +``` + +| 形参 | 含义 | +| --- | --- | +| `H` | 程序计数器 PC(字节码下标) | +| `z` | 字节码整数数组(45636 个) | +| `c` | **宿主全局对象**(页面里就是 `window`)—— `.apply(c, ...)` 的默认 this | +| `E` | **寄存器区 + 求值栈**(同一个数组!)默认 `[[this],[{}]]` | +| `I D U C` | 其它透传参数(本样本用不到) | +| `B` | try 栈(异常帧) | +| `w` | 异常标志(非空即"有异常") | + +主循环:`M = G[z[H++]]()` —— 取 `z[H++]` 当 opcode 下标调用 handler;**handler 返回真值时循环结束**(对应 `RET_TRUE`=19、`IS_EXCEPTION`=1 在异常时)。 + +--- + +## 2. 数据模型(关键,之前所有混乱都出在这里) + +1. **`E` 同时是"寄存器区"和"求值栈"**:`E[0..n-1]` 是寄存器,`E[n..]` 是栈。 +2. **寄存器是"单元数组"**:寄存器 `i` 的**值**是 `E[i][0]`,而 `E[i]` 本身是个数组(`ALLOC_REG i` → `E[i] = []`)。 +3. **"寄存器引用"惯用法**: + - `PUSH_IMM_ARRAY i`(op 31)压入字面数组 `[i]`(这里 `i` 是**寄存器号**,不是数组元素); + - `MAKE_REG_PROP_REF`(op 32)`A=E.pop(); E.push([E[E.pop()][0], A])` → 得到 `[E[i][0], key]`,即"**对寄存器值的属性引用**"。 +4. **引用 = 两元素数组 `[base, key]`**;`GET_PROP`(59)/`SET_PROP`(14) 负责解引用。 +5. 栈操作:`DUP`(2)、`SWAP n`(17,`n` 是相对栈顶的偏移)、`POP`(51)、`REVERSE_TOP2`(54)、`SET_STACK_LEN n`(53,**直接截断/扩张 E 的长度**)、`REPLACE_TOP_IMM v`(64)。 + +> ⚠️ 因为 `E` 一物两用、寄存器有"单元数组"这层壳、且引用是普通二元数组,**任何"按寄存器号做正则匹配"的做法都会失效** —— 必须做真正的数据流/执行。 + +--- + +## 3. 完整 opcode 表(70 槽 / 58 handler / 12 空洞) + +`argc` = handler 体内 `z[H++]` 次数(= 固定操作数字节数);`57` 是动态长度(见 §4)。 +**空洞 opcode**:`7, 16, 21, 24, 27, 40, 43, 44, 50, 58, 63, 67` —— 它们**永远不会**出现在可执行字节码里;一旦在反汇编里看到空洞 opcode,说明**解码失步**(旧线性反汇编器就是这么坏的)。 + +| opcode | argc | handler 源码(VM 内 G 数组第 i 项) | +| --- | --- | --- | +| 0 | 1 | `function () { E[E.length - 1] += String.fromCharCode(z[H++]); }` | +| 1 | 0 | `function () { return !!w; }` | +| 2 | 0 | `function () { E.push(E[E.length - 1]); }` | +| 3 | 0 | `function () { E[E.length - 2] = E[E.length - 2] ^ E.pop(); }` | +| 4 | 0 | `function () { E[E.length - 2] = E[E.length - 2] === E.pop(); }` | +| 5 | 0 | `function () { E[E.length - 2] = E[E.length - 2] % E.pop(); }` | +| 6 | 1 | `function () { var A = z[H++], B = A ? E.slice(-A) : []; E.length -= A, E.push(E.pop().apply(c, B)); }` | +| 7 | - | _(空洞: 无 handler)_ | +| 8 | 0 | `function () { E[E.length - 1] = c[E[E.length - 1]]; }` | +| 9 | 0 | `function () { var A = E.pop(), B = E.pop(); E.push([B[0][B[1]], A]); }` | +| 10 | 0 | `function () { E.push(typeof E.pop()); }` | +| 11 | 0 | `function () { var A = E.pop(); E.push(delete A[0][A[1]]); }` | +| 12 | 0 | `function () { E.push(!E.pop()); }` | +| 13 | 0 | `function () { E[E.length - 2] = E[E.length - 2] == E.pop(); }` | +| 14 | 0 | `function () { var A = E[E.length - 2]; A[0][A[1]] = E[E.length - 1]; }` | +| 15 | 0 | `function () { E[E.length - 2] = E[E.length - 2] > E.pop(); }` | +| 16 | - | _(空洞: 无 handler)_ | +| 17 | 1 | `function () { var A = z[H++], B = E[E.length - 2 - A]; E[E.length - 2 - A] = E.pop(), E.push(B); }` | +| 18 | 0 | `function () { E[E.length - 2] = E[E.length - 2] in E.pop(); }` | +| 19 | 0 | `function () { return !0; }` | +| 20 | 0 | `function () { E[E.length - 2] = E[E.length - 2] >= E.pop(); }` | +| 21 | - | _(空洞: 无 handler)_ | +| 22 | 1 | `function () { E.push(z[H++]); }` | +| 23 | 0 | `function () { E[E.length - 2] = E[E.length - 2] * E.pop(); }` | +| 24 | - | _(空洞: 无 handler)_ | +| 25 | 0 | `function () { E.push(E[E.pop()[0]][0]); }` | +| 26 | 0 | `function () { E[E.length - 1].length ? E.push(E[E.length - 1].shift(), !0) : E.push(undefined, !1); }` | +| 27 | - | _(空洞: 无 handler)_ | +| 28 | 0 | `function () { E.push([c, E.pop()]); }` | +| 29 | 0 | `function () { E.push(null); }` | +| 30 | 0 | `function () { E[E.length - 2] = E[E.length - 2] & E.pop(); }` | +| 31 | 1 | `function () { E.push([z[H++]]); }` | +| 32 | 0 | `function () { var A = E.pop(); E.push([E[E.pop()][0], A]); }` | +| 33 | 0 | `function () { E[E.length - 2] = E[E.length - 2] - E.pop(); }` | +| 34 | 1 | `function () { var A = z[H++], B = A ? E.slice(-A) : [], A = (E.length -= A, E.pop()); E.push(A[0][A[1]].apply(A[0], B)); }` | +| 35 | 0 | `function () { E[E.length - 2] = E[E.length - 2] >> E.pop(); }` | +| 36 | 0 | `function () { E[E.length - 2] = E[E.length - 2] << E.pop(); }` | +| 37 | 1 | `function () { var A = z[H++]; E[E.length - 1] && (H = A); }` | +| 38 | 0 | `function () { var A, B = []; for (A in E.pop()) B.push(A); E.push(B); }` | +| 39 | 0 | `function () { E[E.length - 2] = E[E.length - 2] + E.pop(); }` | +| 40 | - | _(空洞: 无 handler)_ | +| 41 | 1 | `function () { var A = z[H++], B = A ? E.slice(-A) : [], A = (E.length -= A, B.unshift(null), E.pop()); E.push(Q(A[0][A[1]], B)); }` | +| 42 | 0 | `function () { E.push(undefined); }` | +| 43 | - | _(空洞: 无 handler)_ | +| 44 | - | _(空洞: 无 handler)_ | +| 45 | 0 | `function () { E.push(!1); }` | +| 46 | 0 | `function () { E[E[E.length - 2][0]][0] = E[E.length - 1]; }` | +| 47 | 1 | `function () { var A = z[H++]; E[A] = E[A] === undefined ? [] : E[A]; }` | +| 48 | 0 | `function () { B.pop(); }` | +| 49 | 0 | `function () { throw E[E.length - 1]; }` | +| 50 | - | _(空洞: 无 handler)_ | +| 51 | 0 | `function () { E.pop(); }` | +| 52 | 0 | `function () { E[E.length - 2] = E[E.length - 2] / E.pop(); }` | +| 53 | 1 | `function () { E.length = z[H++]; }` | +| 54 | 0 | `function () { E.push([E.pop(), E.pop()].reverse()); }` | +| 55 | 0 | `function () { E.push(""); }` | +| 56 | 2 | `function () { B.push([z[H++], E.length, z[H++]]); }` | +| 57 | 6 | `function () { for (var w = z[H++], Q = [], A = z[H++], B = z[H++], G = [], M = 0; M < A; M++) Q[z[H++]] = E[z[H++]]; for (M = 0; M < B; M++) G[M] = z[H++]; E.push(function g() { var A = Q.slice(0); A[0] = [this], A[1] = [arguments …` | +| 58 | - | _(空洞: 无 handler)_ | +| 59 | 0 | `function () { var A = E.pop(); E.push(A[0][A[1]]); }` | +| 60 | 1 | `function () { H = z[H++]; }` | +| 61 | 1 | `function () { var A = z[H++], B = A ? E.slice(-A) : []; E.length -= A, B.unshift(null), E.push(Q(E.pop(), B)); }` | +| 62 | 0 | `function () { E[E.length - 2] = E[E.length - 2] \| E.pop(); }` | +| 63 | - | _(空洞: 无 handler)_ | +| 64 | 1 | `function () { E[E.length - 1] = z[H++]; }` | +| 65 | 0 | `function () { E[E.length - 2] = E[E.length - 2] >>> E.pop(); }` | +| 66 | 0 | `function () { E.push(!0); }` | +| 67 | - | _(空洞: 无 handler)_ | +| 68 | 1 | `function () { E.push(E[z[H++]][0]); }` | +| 69 | 0 | `function () { w = null; }` | + +--- + +## 4. 闭包与调用约定 + +### 4.1 `CREATE_CLOSURE`(57) —— 操作数布局(动态) + +``` +@pc: 57 target capN parN [reg,reg]*capN [reg]*parN +``` +handler 语义(源码): + +```js +for (var w = z[H++], Q = [], A = z[H++], B = z[H++], G = [], M = 0; M < A; M++) Q[z[H++]] = E[z[H++]]; +for (M = 0; M < B; M++) G[M] = z[H++]; +E.push(function g() { + var A = Q.slice(0); + A[0] = [this], A[1] = [arguments], A[2] = [g]; + for (var B = 0; B < G.length && B < arguments.length; B++) 0 < G[B] && (A[G[B]] = [arguments[B]]); + return __TENCENT_CHAOS_VM(w, z, c, A, I, D, U, C); +}); +``` + +- `Q[capRegIdx] = E[parentRegIdx]` —— **捕获是按"寄存器号 → 寄存器号"成对出现的**(`caps=[r7=r8]` 表示新闭包的 r7 ← 父闭包 r8,**共享同一单元对象**); +- `G` 是形参寄存器号表; +- **调用闭包 = 以 `target` 为新 PC、带着"捕获拷贝 + this/arguments/g"重新进入 VM**。 + +> 🔑 由此得出一条反汇编铁律:**`CREATE_CLOSURE` 的 `target` 是"被调用时才执行"的代码,必须作为反汇编遍历根**,否则大半个程序都算不到(这是旧工具的第二处致命缺陷)。 + +### 4.2 调用类 opcode + +| op | 名字 | this 绑定 | 说明 | +| --- | --- | --- | --- | +| 6 | CALL_FUNC n | `c`(全局) | `E.push(E.pop().apply(c, B))` | +| 34 | CALL_METHOD n | 引用基对象 | `A[0][A[1]].apply(A[0], B)` | +| 61 | NEW_FUNC n | — | 用 `Q(...)` 做 `new` | +| 41 | NEW_METHOD n | — | 同上,参数前插 `null` | +| 28 | BIND_THIS | — | `E.push([c, E.pop()])` 造"以 c 为基"的引用 | + +### 4.3 其它结构 + +- **异常**:`PUSH_TRY`(56) 压 `[catchPC, E.length, catchVarReg]` 到 `B`;`POP_TRY`(48) 弹;`IS_EXCEPTION`(1) 检查 `w`;`CLEAR_EXCEPTION`(69) `w=null`;`THROW`(49)。 +- **属性**:`GET_GLOBAL_PROP`(8) `c[E[-1]]`;`MAKE_PROP_REF`(9) 通用引用;`FOR_IN_KEYS`(38)。 +- **字符串**:`PUSH_EMPTY_STR`(55) 压 `""`,随后一串 `PUSH_STR_CHAR`(0) 逐字符追加 —— 所以**字面串在字节码里是一串 <256 的立即数**(折叠即可还原,`tdc_disasm.py` 已做)。 + +--- + +## 5. 引导流程(bootstrap,实测) + +``` +@00000: SET_STACK_LEN 3 +@00002: ALLOC_REG 2 +@00004: JUMP @1518 +... +@01518: CREATE_CLOSURE target=@7 caps=[] params=[p0->r3] <- 模块工厂(之一) +@01523: PUSH_EMPTY_STR "Array" ... GET_GLOBAL_PROP / NEW_FUNC ... +... +(很快 RET_TRUE 返回) +``` + +**我们的 Python 解释器跑 739 步后 `RET_TRUE` 返回,且寄存器里没有可用的模块闭包** —— 说明: + +> **tdc.js 的顶层只"注册/装配"模块;真正做 XTEA、生成密钥的代码,是在宿主调用进模块时才执行的**(浏览器里最终由 `TDC.getData()` 触发;`tools/tdc_probe.js` 也是这么驱动的)。 + +--- + +## 6. 宿主接口与"如何驱动"(纯 Python 路线的真正缺口) + +- JS 侧调用是 `__TENCENT_CHAOS_VM(0, , window)` → **`c = window`**。 +- VM 本身不碰环境;**环境访问全部通过 `c`**(`GET_GLOBAL_PROP` / `CALL_METHOD` 的基对象)。 +- 因此"能跑出 collect"靠的是:**页面加载 → 模块系统装配 → 宿主调用模块入口 → 模块内部用 `c` 读环境**。 +- 所以纯 Python 静态路线要补的不是 VM,而是**模块系统 + 宿主调用序列**。 + +--- + +## 7. 工具链映射 + +| 工具 | 作用 | 状态 | +| --- | --- | --- | +| `tools/tdc_disasm.py` | 纯 Python:提取字节码 + 可达性 CFG 反汇编(0 非法 opcode) | ✅ 可用(canonical) | +| `tools/tdc_vm_run.py` | 纯 Python:58 个 opcode 的具体解释器 + 宽松 JS 宿主 | 🚧 WIP(跑通顶层引导,未达密钥) | +| `tools/tdc_probe.js` | 深度 Proxy 沙箱驱动真实 tdc.js(**分析参考**,非交付路径) | 分析工具 | +| `tcaptcha/tdc_worker.js` | Node 插桩抓 XTEA 密钥常量(当前唯一 Node 依赖) | 可用·有缓存 | + +--- + +## 8. 解释器路线图(要"彻底理顺"必须补齐的点) + +1. **模块表**:记录每个 `CREATE_CLOSURE` 工厂的 `target`,识别"注册 vs 调用"。 +2. **模块系统语义**:复刻 `require/exports` 式的装配顺序(谁在何时被调用)。 +3. **宿主 `c` 的最小可用面**:`Object/Array/String/Math/JSON/RegExp/Date` + 事件/DOM 桩(严格只补"模块初始化真正读到的",不盲目补)。 +4. **驱动入口**:复刻页面初始化序列,直到进入 XTEA 那段闭包。 +5. **抓取产物**:寄存器中出现的"4 个可打印字符拼成的 32bit 数组" = XTEA 密钥(已确证形态)。 +6. **校验**:与 `extract_xtea_key`(Node)结果逐字对齐,对齐后才敢替换。 + +> 已完成:①字节码提取 ②正确反汇编 ③全部 opcode 语义 ④密钥形态与流向定位(`caps=[r7=r8]`,XTEA 轮 `reg7[(sum>>>11)&3]`,本构建轮加盐 `723726`/`855311`)。 +> 未完成:⑤模块系统 + 宿主驱动(本路线图的 1–4)。 diff --git a/tools/tdc_vm_run.py b/tools/tdc_vm_run.py new file mode 100644 index 0000000..1c9b19b --- /dev/null +++ b/tools/tdc_vm_run.py @@ -0,0 +1,560 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +""" +腾讯天御 Chaos VM —— **纯 Python 具体执行器** (目标: 静态解出 XTEA 密钥, 去掉 Node 依赖) + +思路 +---- +密钥字是 4 个 "ASCII 打包的 4 字符串", 但既不是立即数、也不是任何字面字符串/其子串, +说明它是**运行时算出来的**。所以这里把 VM 的 70 个 opcode 语义 (由 handlers 源码逐一确认) +在 Python 里重新实现, 直接跑字节码, 把寄存器里出现的 "4 个可打印字符拼成的 32bit 数组" 抓出来。 + +VM 模型 (与源码一致): + * `E` 同时是**寄存器区** (E[0..n-1]) 与**求值栈** (E[n..]); + * 寄存器单元是长度为 1 的数组: 值 = E[i][0]; + * `z` = 字节码, `H` = PC, `c` = 宿主全局对象 (window)。 + +用法: + .venv/bin/python tools/tdc_vm_run.py tcaptcha/core_js/tdc_sample.js + KEY=<已知密钥> .venv/bin/python tools/tdc_vm_run.py tdc.js # 命中即打印所在寄存器 +""" +from __future__ import annotations + +import json +import math +import os +import re +import sys +import time +from typing import Any, Dict, List, Optional + +sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) +from tdc_disasm import extract_bytecode # noqa: E402 + + +# --------------------------------------------------------------------------- # +# JS 风格容器: 既支持整数下标, 也支持字符串属性 +# --------------------------------------------------------------------------- # +class JArr(list): + def __init__(self, *a): + super().__init__(*a) + self._ext: Dict[str, Any] = {} + + def __getitem__(self, k): + if isinstance(k, int) or (isinstance(k, str) and k.lstrip("-").isdigit()): + i = int(k) + try: + return list.__getitem__(self, i) + except IndexError: + return None + return self._ext.get(k) + + def __setitem__(self, k, v): + if isinstance(k, int) or (isinstance(k, str) and k.lstrip("-").isdigit()): + i = int(k) + if 0 <= i < len(self): + list.__setitem__(self, i, v) + else: + self._ext[str(i)] = v + else: + self._ext[k] = v + + +JS_UNDEF = object() + + +class Stub: + """未知宿主对象的占位: 可调用、可属性访问、可下标, 一律返回自身/None。""" + + def __init__(self, name="stub"): + self._name = name + + def __call__(self, *a, **k): + return Stub(self._name + "()") + + def __getattr__(self, k): + if k.startswith("_"): + raise AttributeError(k) + return Stub(f"{self._name}.{k}") + + def __getitem__(self, k): + return Stub(f"{self._name}[{k}]") + + def __setitem__(self, k, v): + pass + + def __repr__(self): + return f"<{self._name}>" + + +def _to_host(**kw): + o = JArr() + o._ext.update(kw) + return o + + +def make_host() -> Any: + """最小宿主 (c = window)。未知项退化为 Stub, 保证不因缺属性而崩。""" + win = _to_host() + + class MathMod: + pass + + win._ext.update({ + "Math": Stub("Math"), + "JSON": type("J", (), {"parse": staticmethod(json.loads), "stringify": staticmethod(json.dumps)})(), + "Object": JArr, + "Array": JArr, + "String": str, + "Number": float, + "Boolean": bool, + "Date": int(time.time() * 1000), + "RegExp": Stub("RegExp"), + "Error": Stub("Error"), + "TypeError": Stub("TypeError"), + "Uint8Array": bytearray, + "Uint8ClampedArray": bytearray, + "parseInt": int, + "parseFloat": float, + "encodeURIComponent": lambda s: s, + "decodeURIComponent": lambda s: s, + "atob": lambda s: s, + "btoa": lambda s: s, + "undefined": JS_UNDEF, + "NaN": float("nan"), + }) + return win + + +def getprop(base, key): + """JS 的 base[key] (非严格语义: 对原始值取属性返回 undefined)""" + if isinstance(base, (Stub, JArr)): + return base[key] + if isinstance(base, dict): + return base.get(str(key), JS_UNDEF) + if isinstance(base, list): + return base[int(key)] if isinstance(key, (int, str)) and str(key).lstrip("-").isdigit() and 0 <= int(key) < len(base) else JS_UNDEF + if isinstance(base, str): + return base[int(key)] if isinstance(key, (int, str)) and str(key).lstrip("-").isdigit() and 0 <= int(key) < len(base) else JS_UNDEF + return JS_UNDEF # number/bool/null/undefined: 属性访问为 undefined + + +def setprop(base, key, val): + """JS 的 base[key] = val (非严格语义: 对原始值赋值静默忽略)""" + if isinstance(base, Stub): + return + if isinstance(base, JArr): + base[key] = val + return + if isinstance(base, dict): + base[str(key)] = val + return + if isinstance(base, list): + i = int(key) + if 0 <= i < len(base): + base[i] = val + else: + base.append(val) + return + return # 原始值: 静默忽略 + + +def as_int(v): + if isinstance(v, bool): + return 1 if v else 0 + if v is JS_UNDEF or v is None: + return 0 + if isinstance(v, (int, float)): + return int(v) & 0xFFFFFFFF + if isinstance(v, str): + return len(v) and (ord(v[0]) & 0xFFFFFFFF) or 0 + return 0 + + +def truthy(v): + if v is JS_UNDEF or v is None or v is False: + return False + if isinstance(v, (int, float)): + return v != 0 + if isinstance(v, str): + return len(v) > 0 + return True + + +# --------------------------------------------------------------------------- # +class VM: + def __init__(self, z: List[int], c, max_steps: int = 20_000_000): + self.z = z + self.c = c + self.E: List[Any] = [] # 寄存器区 + 栈 + self.B: List[Any] = [] # try 栈 + self.w = None # 异常标志 + self.H = 0 + self.steps = 0 + self.max_steps = max_steps + self.done = False + self.ret = None + self.key_hits: List[Any] = [] + + # ---- 工具 + def pu(self): + return self.E.pop() + + def look(self): + self.record_cell(self.E[-1]) + + def record_cell(self, v): + if isinstance(v, list) and len(v) == 4 and all(isinstance(x, int) for x in v): + if all(32 <= (x & 0xFF) < 127 and 32 <= ((x >> 24) & 0xFF) < 127 for x in v): + packed = b"".join(x.to_bytes(4, "big") for x in v) + if all(32 <= b < 127 for b in packed): + self.key_hits.append(list(v)) + + # ---- 主循环 + def run(self): + z = self.z + while not self.done and self.H < len(z): + self.steps += 1 + if self.steps > self.max_steps: + raise RuntimeError("step limit exceeded") + op = z[self.H]; self.H += 1 + h = self.OP.get(op) + if h is None: + raise RuntimeError(f"unknown opcode {op} at pc {self.H-1}") + if h() is True: + self.done = True + return self.ret + + # ------------------------------------------------------------------ ops + def _run(self): + z, E = self.z, self.E + OP = {} + + def op(n): + def deco(f): + OP[n] = f + return f + return deco + + @op(0) # PUSH_STR_CHAR + def _0(): + E[-1] = (E[-1] if isinstance(E[-1], str) else "") + chr(z[self.H]); self.H += 1 + + @op(1) # IS_EXCEPTION -> 结束 + def _1(): + if truthy(self.w): + self.ret = self.w + return True + return None + + @op(2) + def _2(): + E.append(E[-1]) + + def binop(f): + def g(): + b = E.pop(); E[-2] = f(E[-2], b) + return g + + OP[3] = binop(lambda a, b: as_int(a) ^ as_int(b)) + OP[4] = binop(lambda a, b: a is b or a == b) + OP[5] = binop(lambda a, b: (as_int(a) % as_int(b)) if as_int(b) else float("nan")) + OP[13] = binop(lambda a, b: a == b) + OP[15] = binop(lambda a, b: as_int(a) > as_int(b)) + OP[20] = binop(lambda a, b: as_int(a) >= as_int(b)) + OP[23] = binop(lambda a, b: (as_int(a) * as_int(b)) & 0xFFFFFFFF) + OP[30] = binop(lambda a, b: as_int(a) & as_int(b)) + OP[33] = binop(lambda a, b: (as_int(a) - as_int(b)) & 0xFFFFFFFF) + OP[35] = binop(lambda a, b: as_int(a) >> (as_int(b) & 31)) + OP[36] = binop(lambda a, b: (as_int(a) << (as_int(b) & 31)) & 0xFFFFFFFF) + OP[39] = binop(lambda a, b: ((as_int(a) + as_int(b)) & 0xFFFFFFFF) if (isinstance(a, int) and isinstance(b, int)) else (a + b)) + OP[52] = binop(lambda a, b: (as_int(a) / as_int(b)) if as_int(b) else float("nan")) + OP[62] = binop(lambda a, b: as_int(a) | as_int(b)) + OP[65] = binop(lambda a, b: (as_int(a) & 0xFFFFFFFF) >> (as_int(b) & 31)) + OP[18] = binop(lambda a, b: isinstance(b, (list, dict, JArr)) and (a in (b._ext if isinstance(b, JArr) else b))) + + @op(6) # CALL_FUNC n + def _6(): + n = z[self.H]; self.H += 1 + args = E[-n:] if n else [] + del E[len(E) - n:] + fn = E.pop() + E.append(self.call(fn, args, None)) + + @op(8) # GET_GLOBAL_PROP + def _8(): + E[-1] = getprop(self.c, E[-1]) + + @op(9) # MAKE_PROP_REF + def _9(): + a = E.pop(); b = E.pop() + E.append([getprop(b[0], b[1]), a]) + + @op(10) + def _10(): + E[-1] = type(E[-1]).__name__ + + @op(11) + def _11(): + a = E.pop(); E.append(True) + + @op(12) + def _12(): + E[-1] = not truthy(E[-1]) + + @op(14) # SET_PROP + def _14(): + a = E[-2]; setprop(a[0], a[1], E[-1]) + + @op(17) # SWAP n + def _17(): + n = z[self.H]; self.H += 1 + i = len(E) - 2 - n + b = E[i]; E[i] = E.pop(); E.append(b) + + @op(19) # RET_TRUE + def _19(): + self.ret = True + return True + + @op(22) # PUSH_IMM + def _22(): + E.append(z[self.H]); self.H += 1 + + @op(25) # LOAD_REG_INDIRECT + def _25(): + cell = E[E.pop()[0]] + E.append(cell[0] if cell else JS_UNDEF) + + @op(26) # ITER_NEXT + def _26(): + it = E[-1] + if it: + E.append(it.pop(0)); E.append(True) + else: + E.append(JS_UNDEF); E.append(False) + + @op(28) + def _28(): + E.append([self.c, E.pop()]) + + @op(29) + def _29(): + E.append(None) + + @op(31) # PUSH_IMM_ARRAY + def _31(): + E.append(JArr([z[self.H]])); self.H += 1 + + @op(32) # MAKE_REG_PROP_REF + def _32(): + a = E.pop() + idx = E.pop() + cell = E[idx[0]] if isinstance(idx, list) else E[idx] + E.append([cell[0] if isinstance(cell, list) and cell else JS_UNDEF, a]) + + @op(34) # CALL_METHOD n + def _34(): + n = z[self.H]; self.H += 1 + args = E[-n:] if n else [] + del E[len(E) - n:] + ref = E.pop() + E.append(self.call(getprop(ref[0], ref[1]), args, ref[0])) + + @op(37) # JUMP_IF_TRUE + def _37(): + t = z[self.H]; self.H += 1 + if truthy(E[-1]): + self.H = t + + @op(38) # FOR_IN_KEYS + def _38(): + o = E.pop() + E.append(JArr(list(o._ext.keys()) if isinstance(o, JArr) else list(o.keys()) if isinstance(o, dict) else [])) + + @op(41) # NEW_METHOD n + def _41(): + n = z[self.H]; self.H += 1 + args = E[-n:] if n else [] + del E[len(E) - n:] + args.insert(0, None) + fn = E.pop() + E.append(self.new(fn, args)) + + @op(42) + def _42(): + E.append(JS_UNDEF) + + @op(45) + def _45(): + E.append(False) + + @op(46) # STORE_REG + def _46(): + idx = E[-2][0] + cell = E[idx] + if not isinstance(cell, list): + cell = [] + E[idx] = cell + v = E[-1] + if cell: + cell[0] = v + else: + cell.append(v) + self.record_cell(v) + + @op(47) # ALLOC_REG + def _47(): + a = z[self.H]; self.H += 1 + while len(E) <= a: + E.append(JS_UNDEF) + if not isinstance(E[a], list): + E[a] = [] + + @op(48) + def _48(): + self.B.pop() + + @op(49) # THROW + def _49(): + raise RuntimeError("VM throw") + + @op(51) + def _51(): + E.pop() + + @op(53) # SET_STACK_LEN + def _53(): + n = z[self.H]; self.H += 1 + while len(E) < n: + E.append(JS_UNDEF) + del E[n:] + + @op(54) + def _54(): + a = E.pop(); b = E.pop() + E.append(JArr([a, b])) + + @op(55) + def _55(): + E.append("") + + @op(56) # PUSH_TRY + def _56(): + self.H += 2 + + @op(57) # CREATE_CLOSURE + def _57(): + target = z[self.H]; self.H += 1 + cap = z[self.H]; self.H += 1 + par = z[self.H]; self.H += 1 + caps = [] + for _ in range(cap): + q = z[self.H]; self.H += 1 + r = z[self.H]; self.H += 1 + caps.append((q, r)) + params = [] + for _ in range(par): + params.append(z[self.H]); self.H += 1 + E.append(("closure", target, caps, params)) + + @op(59) # GET_PROP + def _59(): + a = E.pop() + E.append(getprop(a[0], a[1])) + + @op(60) # JUMP + def _60(): + self.H = z[self.H] + + @op(61) # NEW_FUNC n + def _61(): + n = z[self.H]; self.H += 1 + args = E[-n:] if n else [] + del E[len(E) - n:] + args.insert(0, None) + fn = E.pop() + E.append(self.new(fn, args)) + + @op(64) # REPLACE_TOP_IMM + def _64(): + E[-1] = z[self.H]; self.H += 1 + + @op(66) + def _66(): + E.append(True) + + @op(68) # LOAD_REG_IMM + def _68(): + a = z[self.H]; self.H += 1 + cell = E[a] if a < len(E) else None + E.append(cell[0] if isinstance(cell, list) and cell else JS_UNDEF) + + @op(69) + def _69(): + self.w = None + + self.OP = OP + return self.run() + + # ---- 调用/构造 + def call(self, fn, args, this): + if isinstance(fn, tuple) and fn and fn[0] == "closure": + sub = VM(self.z, self.c, self.max_steps - self.steps) + sub.key_hits = self.key_hits # 子 VM 共享命中列表 + sub.E = [JArr() for _ in range(32)] + sub.E[0] = JArr([this]); sub.E[1] = JArr([JArr(args)]); sub.E[2] = JArr([fn]) + for (q, r) in fn[2]: + sub.E[q] = self.E[r] + for i, r in enumerate(fn[3]): + sub.E[r] = JArr([args[i] if i < len(args) else JS_UNDEF]) + sub.H = fn[1] + try: + v = sub._run() + self.steps += sub.steps + return v + except Exception: + return JS_UNDEF + if isinstance(fn, Stub): + return Stub("call") + return JS_UNDEF + + def new(self, fn, args): + return self.call(fn, args, {}) + + +def main() -> int: + path = sys.argv[1] if len(sys.argv) > 1 else "tcaptcha/core_js/tdc_sample.js" + js = open(path, encoding="utf-8", errors="replace").read() + z = extract_bytecode(js) + known = os.environ.get("KEY") + known_key = [int(x) for x in known.split(",")] if known else None + print(f"bytecode={len(z)} known_key={known_key}") + + vm = VM(z, make_host(), max_steps=30_000_000) + try: + vm._run() + except Exception as e: + print("VM halted with:", type(e).__name__, str(e)[:200]) + print("steps:", vm.steps, "done:", vm.done, "ret:", str(vm.ret)[:80]) + + # tdc.js 顶层只"注册"模块工厂; 这里主动调用寄存器里保存的闭包 (模拟模块系统/宿主调用) + closures = [cell[0] for cell in vm.E + if isinstance(cell, list) and cell and isinstance(cell[0], tuple) + and cell[0] and cell[0][0] == "closure"] + print("registered closures in registers:", len(closures)) + for i, cl in enumerate(closures): + try: + vm.call(cl, [Stub("arg")], {}) + except Exception as e: + print(f" closure#{i} (target=@{cl[1]}) raised {type(e).__name__}: {str(e)[:80]}") + print("total steps after invoking closures:", vm.steps) + hits = [h for h in vm.key_hits if known_key is None or h == known_key] + print("candidate 4-char packed arrays:", len(hits)) + for h in hits[:10]: + print(" ", h, "->", b"".join(x.to_bytes(4, "big") for x in h)) + return 0 + + +if __name__ == "__main__": + raise SystemExit(main())