Miasm 是一个免费开源 (GPLv2) 逆向工程框架。 Miasm 旨在分析/修改/生成二进制程序。以下是功能的非详尽列表:
更多示例和演示请参阅官方博客。
导入 Miasm x86 架构:
>>> from miasm.arch.x86.arch import mn_x86
>>> from miasm.core.locationdb import LocationDB
获取位置数据库:
>>> loc_db = LocationDB()
组装一条线:
>>> l = mn_x86.fromstring( ' XOR ECX, ECX ' , loc_db, 32 )
>>> print (l)
XOR ECX, ECX
>>> mn_x86.asm(l)
['1xc9', '3xc9', 'g1xc9', 'g3xc9']
修改操作数:
>>> l.args[ 0 ] = mn_x86.regs. EAX
>>> print (l)
XOR EAX, ECX
>>> a = mn_x86.asm(l)
>>> print (a)
['1xc8', '3xc1', 'g1xc8', 'g3xc1']
反汇编结果:
>>> print (mn_x86.dis(a[ 0 ], 32 ))
XOR EAX, ECX
使用Machine
抽象:
>>> from miasm.analysis.machine import Machine
>>> mn = Machine( ' x86_32 ' ).mn
>>> print (mn.dis( ' x33x30 ' , 32 ))
XOR ESI, DWORD PTR [EAX]
对于 MIPS:
>>> mn = Machine( ' mips32b ' ).mn
>>> print (mn.dis( b ' x97xa3x00 ' , " b " ))
LHU V1, 0x20(SP)
创建指令:
>>> machine = Machine( ' arml ' )
>>> instr = machine.mn.dis( ' x00 x88xe0 ' , ' l ' )
>>> print (instr)
ADD R2, R8, R0
创建一个中间表示对象:
>>> lifter = machine.lifter_model_call(loc_db)
创建一个空的 ircfg:
>>> ircfg = lifter.new_ircfg()
向池中添加指令:
>>> lifter.add_instr_to_ircfg(instr, ircfg)
打印当前池:
>>> for lbl, irblock in ircfg.blocks.items():
... print (irblock)
loc_0:
R2 = R8 + R0
IRDst = loc_4
使用 IR,例如通过获得副作用:
>>> for lbl, irblock in ircfg.blocks.items():
... for assignblk in irblock:
... rw = assignblk.get_rw()
... for dst, reads in rw.items():
... print ( ' read: ' , [ str (x) for x in reads])
... print ( ' written: ' , dst)
... print ()
...
read: ['R8', 'R0']
written: R2
read: []
written: IRDst
有关 Miasm IR 的更多信息请参阅相应的 Jupyter Notebook。
给出一个shellcode:
00000000 8d4904 lea ecx, [ecx+0x4]
00000003 8d5b01 lea ebx, [ebx+0x1]
00000006 80f901 cmp cl, 0x1
00000009 7405 jz 0x10
0000000b 8d5bff lea ebx, [ebx-1]
0000000e eb03 jmp 0x13
00000010 8d5b01 lea ebx, [ebx+0x1]
00000013 89d8 mov eax, ebx
00000015 c3 ret
>>> s = b ' x8d I x04x8d [ x01x80xf9x01 t x05x8d [ xffxebx03x8d [ x01x89xd8xc3 '
通过Container
抽象导入 shellcode:
>>> from miasm.analysis.binary import Container
>>> c = Container.from_string(s, loc_db)
>>> c
反汇编地址0
处的 shellcode:
>>> from miasm.analysis.machine import Machine
>>> machine = Machine( ' x86_32 ' )
>>> mdis = machine.dis_engine(c.bin_stream, loc_db = loc_db)
>>> asmcfg = mdis.dis_multiblock( 0 )
>>> for block in asmcfg.blocks:
... print (block)
...
loc_0
LEA ECX, DWORD PTR [ECX + 0x4]
LEA EBX, DWORD PTR [EBX + 0x1]
CMP CL, 0x1
JZ loc_10
-> c_next:loc_b c_to:loc_10
loc_10
LEA EBX, DWORD PTR [EBX + 0x1]
-> c_next:loc_13
loc_b
LEA EBX, DWORD PTR [EBX + 0xFFFFFFFF]
JMP loc_13
-> c_to:loc_13
loc_13
MOV EAX, EBX
RET
使用堆栈初始化 JIT 引擎:
>>> jitter = machine.jitter(loc_db, jit_type = ' python ' )
>>> jitter.init_stack()
将 shellcode 添加到任意内存位置:
>>> run_addr = 0x 40000000
>>> from miasm.jitter.csts import PAGE_READ , PAGE_WRITE
>>> jitter.vm.add_memory_page(run_addr, PAGE_READ | PAGE_WRITE , s)
创建一个哨兵来捕获 shellcode 的返回:
def code_sentinelle ( jitter ):
jitter . running = False
jitter . pc = 0
return True
> >> jitter . add_breakpoint ( 0x1337beef , code_sentinelle )
> >> jitter . push_uint32_t ( 0x1337beef )
活动日志:
>>> jitter.set_trace_log()
在任意地址运行:
>>> jitter.init_run(run_addr)
>>> jitter.continue_run()
RAX 0000000000000000 RBX 0000000000000000 RCX 0000000000000000 RDX 0000000000000000
RSI 0000000000000000 RDI 0000000000000000 RSP 000000000123FFF8 RBP 0000000000000000
zf 0000000000000000 nf 0000000000000000 of 0000000000000000 cf 0000000000000000
RIP 0000000040000000
40000000 LEA ECX, DWORD PTR [ECX+0x4]
RAX 0000000000000000 RBX 0000000000000000 RCX 0000000000000004 RDX 0000000000000000
RSI 0000000000000000 RDI 0000000000000000 RSP 000000000123FFF8 RBP 0000000000000000
zf 0000000000000000 nf 0000000000000000 of 0000000000000000 cf 0000000000000000
....
4000000e JMP loc_0000000040000013:0x40000013
RAX 0000000000000000 RBX 0000000000000000 RCX 0000000000000004 RDX 0000000000000000
RSI 0000000000000000 RDI 0000000000000000 RSP 000000000123FFF8 RBP 0000000000000000
zf 0000000000000000 nf 0000000000000000 of 0000000000000000 cf 0000000000000000
RIP 0000000040000013
40000013 MOV EAX, EBX
RAX 0000000000000000 RBX 0000000000000000 RCX 0000000000000004 RDX 0000000000000000
RSI 0000000000000000 RDI 0000000000000000 RSP 000000000123FFF8 RBP 0000000000000000
zf 0000000000000000 nf 0000000000000000 of 0000000000000000 cf 0000000000000000
RIP 0000000040000013
40000015 RET
>>>
与抖动交互:
>>> jitter.vm
ad 1230000 size 10000 RW_ hpad 0x2854b40
ad 40000000 size 16 RW_ hpad 0x25e0ed0
>>> hex (jitter.cpu. EAX )
'0x0L'
>>> jitter.cpu. ESI = 12
初始化IR池:
>>> lifter = machine.lifter_model_call(loc_db)
>>> ircfg = lifter.new_ircfg_from_asmcfg(asmcfg)
使用默认符号值初始化引擎:
>>> from miasm.ir.symbexec import SymbolicExecutionEngine
>>> sb = SymbolicExecutionEngine(lifter)
启动执行:
>>> symbolic_pc = sb.run_at(ircfg, 0 )
>>> print (symbolic_pc)
((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
相同,带有步骤日志(仅显示更改):
>>> sb = SymbolicExecutionEngine(lifter, machine.mn.regs.regs_init)
>>> symbolic_pc = sb.run_at(ircfg, 0 , step = True )
Instr LEA ECX, DWORD PTR [ECX + 0x4]
Assignblk:
ECX = ECX + 0x4
________________________________________________________________________________
ECX = ECX + 0x4
________________________________________________________________________________
Instr LEA EBX, DWORD PTR [EBX + 0x1]
Assignblk:
EBX = EBX + 0x1
________________________________________________________________________________
EBX = EBX + 0x1
ECX = ECX + 0x4
________________________________________________________________________________
Instr CMP CL, 0x1
Assignblk:
zf = (ECX[0:8] + -0x1)?(0x0,0x1)
nf = (ECX[0:8] + -0x1)[7:8]
pf = parity((ECX[0:8] + -0x1) & 0xFF)
of = ((ECX[0:8] ^ (ECX[0:8] + -0x1)) & (ECX[0:8] ^ 0x1))[7:8]
cf = (((ECX[0:8] ^ 0x1) ^ (ECX[0:8] + -0x1)) ^ ((ECX[0:8] ^ (ECX[0:8] + -0x1)) & (ECX[0:8] ^ 0x1)))[7:8]
af = ((ECX[0:8] ^ 0x1) ^ (ECX[0:8] + -0x1))[4:5]
________________________________________________________________________________
af = (((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[4:5]
pf = parity((ECX + 0x4)[0:8] + 0xFF)
zf = ((ECX + 0x4)[0:8] + 0xFF)?(0x0,0x1)
ECX = ECX + 0x4
of = ((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1))[7:8]
nf = ((ECX + 0x4)[0:8] + 0xFF)[7:8]
cf = (((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1)) ^ ((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[7:8]
EBX = EBX + 0x1
________________________________________________________________________________
Instr JZ loc_key_1
Assignblk:
IRDst = zf?(loc_key_1,loc_key_2)
EIP = zf?(loc_key_1,loc_key_2)
________________________________________________________________________________
af = (((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[4:5]
EIP = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
pf = parity((ECX + 0x4)[0:8] + 0xFF)
IRDst = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
zf = ((ECX + 0x4)[0:8] + 0xFF)?(0x0,0x1)
ECX = ECX + 0x4
of = ((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1))[7:8]
nf = ((ECX + 0x4)[0:8] + 0xFF)[7:8]
cf = (((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1)) ^ ((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[7:8]
EBX = EBX + 0x1
________________________________________________________________________________
>>>
使用具体的 ECX 重试执行。在这里,符号/并发执行到达 shellcode 的末尾:
>>> from miasm.expression.expression import ExprInt
>>> sb.symbols[machine.mn.regs. ECX ] = ExprInt( - 3 , 32 )
>>> symbolic_pc = sb.run_at(ircfg, 0 , step = True )
Instr LEA ECX, DWORD PTR [ECX + 0x4]
Assignblk:
ECX = ECX + 0x4
________________________________________________________________________________
af = (((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[4:5]
EIP = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
pf = parity((ECX + 0x4)[0:8] + 0xFF)
IRDst = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
zf = ((ECX + 0x4)[0:8] + 0xFF)?(0x0,0x1)
ECX = 0x1
of = ((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1))[7:8]
nf = ((ECX + 0x4)[0:8] + 0xFF)[7:8]
cf = (((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1)) ^ ((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[7:8]
EBX = EBX + 0x1
________________________________________________________________________________
Instr LEA EBX, DWORD PTR [EBX + 0x1]
Assignblk:
EBX = EBX + 0x1
________________________________________________________________________________
af = (((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[4:5]
EIP = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
pf = parity((ECX + 0x4)[0:8] + 0xFF)
IRDst = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
zf = ((ECX + 0x4)[0:8] + 0xFF)?(0x0,0x1)
ECX = 0x1
of = ((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1))[7:8]
nf = ((ECX + 0x4)[0:8] + 0xFF)[7:8]
cf = (((((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8]) & ((ECX + 0x4)[0:8] ^ 0x1)) ^ ((ECX + 0x4)[0:8] + 0xFF) ^ (ECX + 0x4)[0:8] ^ 0x1)[7:8]
EBX = EBX + 0x2
________________________________________________________________________________
Instr CMP CL, 0x1
Assignblk:
zf = (ECX[0:8] + -0x1)?(0x0,0x1)
nf = (ECX[0:8] + -0x1)[7:8]
pf = parity((ECX[0:8] + -0x1) & 0xFF)
of = ((ECX[0:8] ^ (ECX[0:8] + -0x1)) & (ECX[0:8] ^ 0x1))[7:8]
cf = (((ECX[0:8] ^ 0x1) ^ (ECX[0:8] + -0x1)) ^ ((ECX[0:8] ^ (ECX[0:8] + -0x1)) & (ECX[0:8] ^ 0x1)))[7:8]
af = ((ECX[0:8] ^ 0x1) ^ (ECX[0:8] + -0x1))[4:5]
________________________________________________________________________________
af = 0x0
EIP = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
pf = 0x1
IRDst = ((ECX + 0x4)[0:8] + 0xFF)?(0xB,0x10)
zf = 0x1
ECX = 0x1
of = 0x0
nf = 0x0
cf = 0x0
EBX = EBX + 0x2
________________________________________________________________________________
Instr JZ loc_key_1
Assignblk:
IRDst = zf?(loc_key_1,loc_key_2)
EIP = zf?(loc_key_1,loc_key_2)
________________________________________________________________________________
af = 0x0
EIP = 0x10
pf = 0x1
IRDst = 0x10
zf = 0x1
ECX = 0x1
of = 0x0
nf = 0x0
cf = 0x0
EBX = EBX + 0x2
________________________________________________________________________________
Instr LEA EBX, DWORD PTR [EBX + 0x1]
Assignblk:
EBX = EBX + 0x1
________________________________________________________________________________
af = 0x0
EIP = 0x10
pf = 0x1
IRDst = 0x10
zf = 0x1
ECX = 0x1
of = 0x0
nf = 0x0
cf = 0x0
EBX = EBX + 0x3
________________________________________________________________________________
Instr LEA EBX, DWORD PTR [EBX + 0x1]
Assignblk:
IRDst = loc_key_3
________________________________________________________________________________
af = 0x0
EIP = 0x10
pf = 0x1
IRDst = 0x13
zf = 0x1
ECX = 0x1
of = 0x0
nf = 0x0
cf = 0x0
EBX = EBX + 0x3
________________________________________________________________________________
Instr MOV EAX, EBX
Assignblk:
EAX = EBX
________________________________________________________________________________
af = 0x0
EIP = 0x10
pf = 0x1
IRDst = 0x13
zf = 0x1
ECX = 0x1
of = 0x0
nf = 0x0
cf = 0x0
EBX = EBX + 0x3
EAX = EBX + 0x3
________________________________________________________________________________
Instr RET
Assignblk:
IRDst = @32[ESP[0:32]]
ESP = {ESP[0:32] + 0x4 0 32}
EIP = @32[ESP[0:32]]
________________________________________________________________________________
af = 0x0
EIP = @32[ESP]
pf = 0x1
IRDst = @32[ESP]
zf = 0x1
ECX = 0x1
of = 0x0
nf = 0x0
cf = 0x0
EBX = EBX + 0x3
ESP = ESP + 0x4
EAX = EBX + 0x3
________________________________________________________________________________
>>>
Miasm 嵌入了自己的反汇编程序、中间语言和指令语义。它是用 Python 编写的。
为了模拟代码,它使用 LLVM、GCC、Clang 或 Python 来 JIT 中间表示。它可以模拟 shellcode 和全部或部分二进制文件。可以执行 Python 回调来与执行进行交互,例如模拟库函数效果。
doc 文件夹中提供了一些文档资源。
可以使用自动生成的文档:
瘴气用途:
要启用代码 JIT,必须使用以下模块之一:
“可选”Miasm 还可以使用:
要使用抖动,建议使用 GCC 或 LLVM
pip install llvmlite
或从 llvmlite 安装$ cd miasm_directory
$ python setup.py build
$ sudo python setup.py install
如果某个抖动模块编译期间出现问题,Miasm 将跳过该错误并禁用相应的模块(请参阅编译输出)。
大多数 Miasm 的 IDA 插件都使用 Miasm 功能的子集。让它们工作的一个快速方法是添加:
pyparsing.py
到C:...IDApython
或pip install pyparsing
miasm/miasm
目录到C:...IDApython
除 JITter 相关功能外的所有功能都将可用。如需更完整的安装,请参阅上面的段落。
Miasm 附带一组回归测试。要运行所有这些:
cd miasm_directory/test
# Run tests using our own test runner
python test_all.py
# Run tests using standard frameworks (slower, require 'parameterized')
python -m unittest test_all.py # sequential, requires 'unittest'
python -m pytest test_all.py # sequential, requires 'pytest'
python -m pytest -n auto test_all.py # parallel, requires 'pytest' and 'pytest-xdist'
可以指定一些选项:
-m
-c
-t long
(不包括长测试)