LyScript 实现应用层钩子扫描器

Capstone 是一个轻量级的多平台、多架构的反汇编框架，该模块支持目前所有通用操作系统，反汇编架构几乎全部支持，本篇文章将运用LyScript插件结合Capstone反汇编引擎实现一个钩子扫描器。

插件地址：https://github.com/lyshark/LyScript

要实现应用层钩子扫描，我们需要得到程序内存文件的机器码以及磁盘中的机器码，并通过capstone这个第三方反汇编引擎，对两者进行反汇编，最后逐条对比汇编指令，实现进程钩子扫描的效果。

通过LyScript插件读取出内存中的机器码，然后交给第三方反汇编库执行，并将结果输出成字典格式。

#coding: utf-8
import binascii,os,sys
import pefile
from capstone import *
from LyScript32 import MyDebug

# 得到内存反汇编代码
def get_memory_disassembly(address,offset,len):
    # 反汇编列表
    dasm_memory_dict = []

    # 内存列表
    ref_memory_list = bytearray()

    # 读取数据
    for index in range(offset,len):
        char = dbg.read_memory_byte(address + index)
        ref_memory_list.append(char)

    # 执行反汇编
    md = Cs(CS_ARCH_X86,CS_MODE_32)
    for item in md.disasm(ref_memory_list,0x1):
        addr = int(pe_base) + item.address
        dasm_memory_dict.append({"address": str(addr), "opcode": item.mnemonic + " " + item.op_str})
    return dasm_memory_dict

if __name__ == "__main__":
    dbg = MyDebug()
    dbg.connect()

    pe_base = dbg.get_local_base()
    pe_size = dbg.get_local_size()

    print("模块基地址: {}".format(hex(pe_base)))
    print("模块大小: {}".format(hex(pe_size)))

    # 得到内存反汇编代码
    dasm_memory_list = get_memory_disassembly(pe_base,0,pe_size)
    print(dasm_memory_list)

    dbg.close()

效果如下：

我们将文件反汇编也写一下，然后让其对比，这样就可以实现扫描内存与文件中的汇编指令是否一致。

#coding: utf-8
import binascii,os,sys
import pefile
from capstone import *
from LyScript32 import MyDebug

# 得到内存反汇编代码
def get_memory_disassembly(address,offset,len):
    # 反汇编列表
    dasm_memory_dict = []

    # 内存列表
    ref_memory_list = bytearray()

    # 读取数据
    for index in range(offset,len):
        char = dbg.read_memory_byte(address + index)
        ref_memory_list.append(char)

    # 执行反汇编
    md = Cs(CS_ARCH_X86,CS_MODE_32)
    for item in md.disasm(ref_memory_list,0x1):
        addr = int(pe_base) + item.address
        dic = {"address": str(addr), "opcode": item.mnemonic + " " + item.op_str}
        dasm_memory_dict.append(dic)
    return dasm_memory_dict

# 反汇编文件中的机器码
def get_file_disassembly(path):
    opcode_list = []
    pe = pefile.PE(path)
    ImageBase = pe.OPTIONAL_HEADER.ImageBase

    for item in pe.sections:
        if str(item.Name.decode('UTF-8').strip(b'\x00'.decode())) == ".text":
            # print("虚拟地址: 0x%.8X 虚拟大小: 0x%.8X" %(item.VirtualAddress,item.Misc_VirtualSize))
            VirtualAddress = item.VirtualAddress
            VirtualSize = item.Misc_VirtualSize
            ActualOffset = item.PointerToRawData
    StartVA = ImageBase + VirtualAddress
    StopVA = ImageBase + VirtualAddress + VirtualSize
    with open(path,"rb") as fp:
        fp.seek(ActualOffset)
        HexCode = fp.read(VirtualSize)

    md = Cs(CS_ARCH_X86, CS_MODE_32)
    for item in md.disasm(HexCode, 0):
        addr = hex(int(StartVA) + item.address)
        dic = {"address": str(addr) , "opcode": item.mnemonic + " " + item.op_str}
        # print("{}".format(dic))
        opcode_list.append(dic)
    return opcode_list

if __name__ == "__main__":
    dbg = MyDebug()
    dbg.connect()

    pe_base = dbg.get_local_base()
    pe_size = dbg.get_local_size()

    print("模块基地址: {}".format(hex(pe_base)))
    print("模块大小: {}".format(hex(pe_size)))

    # 得到内存反汇编代码
    dasm_memory_list = get_memory_disassembly(pe_base,0,pe_size)
    dasm_file_list = get_file_disassembly("d://win32project1.exe")

    # 循环对比内存与文件中的机器码
    for index in range(0,len(dasm_file_list)):
        if dasm_memory_list[index] != dasm_file_list[index]:
            print("地址: {:8} --> 内存反汇编: {:32} --> 磁盘反汇编: {:32}".
                  format(dasm_memory_list[index].get("address"),dasm_memory_list[index].get("opcode"),dasm_file_list[index].get("opcode")))
    dbg.close()