binary-analysis-patterns

Master binary analysis patterns including disassembly, decompilation, control flow analysis, and code pattern recognition. Use when analyzing executables, understanding compiled code, or performing static analysis on binaries.

Ir para a instalação

Repositório: oimiragieo/agent-studio
Última atividade na origem: 21 de abril de 2026 às 23:45
Idioma detectado do SKILL.md: inglês
Estrelas: 36
Forks: 6

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

Voltar à pesquisa Voltar à instalação

name	binary-analysis-patterns
description	Master binary analysis patterns including disassembly, decompilation, control flow analysis, and code pattern recognition. Use when analyzing executables, understanding compiled code, or performing static analysis on binaries.
version	1.1.0
model	sonnet
invoked_by	["reverse-engineer","security-architect"]
tools	["Read","Write","Edit","Bash","Glob","Grep"]
verified	true
lastVerifiedAt	"2026-02-22T00:00:00.000Z"
source	builtin
trust_score	100
provenance_sha	e85538ff632da926

Binary Analysis Patterns

Security Notice

AUTHORIZED USE ONLY: These skills are for DEFENSIVE security analysis and authorized research:

Authorized pentesting engagements with written authorization
CTF competitions and security research
Defensive security and malware analysis
Security research with proper disclosure
Educational purposes in controlled environments

NEVER use for:

Creating or enhancing malicious code
Unauthorized access to systems
Bypassing software licensing illegitimately
Intellectual property theft
Any illegal activities

Comprehensive patterns and techniques for analyzing compiled binaries, understanding assembly code, and reconstructing program logic.

Disassembly Fundamentals

x86-64 Instruction Patterns

Function Prologue/Epilogue

; Standard prologue
push rbp           ; Save base pointer
mov rbp, rsp       ; Set up stack frame
sub rsp, 0x20      ; Allocate local variables

; Leaf function (no calls)
; May skip frame pointer setup
sub rsp, 0x18      ; Just allocate locals

; Standard epilogue
mov rsp, rbp       ; Restore stack pointer
pop rbp            ; Restore base pointer
ret

; Leave instruction (equivalent)
leave              ; mov rsp, rbp; pop rbp
ret

Calling Conventions

System V AMD64 (Linux, macOS)

; Arguments: RDI, RSI, RDX, RCX, R8, R9, then stack
; Return: RAX (and RDX for 128-bit)
; Caller-saved: RAX, RCX, RDX, RSI, RDI, R8-R11
; Callee-saved: RBX, RBP, R12-R15

; Example: func(a, b, c, d, e, f, g)
mov rdi, [a]       ; 1st arg
mov rsi, [b]       ; 2nd arg
mov rdx, [c]       ; 3rd arg
mov rcx, [d]       ; 4th arg
mov r8, [e]        ; 5th arg
mov r9, [f]        ; 6th arg
push [g]           ; 7th arg on stack
call func

Microsoft x64 (Windows)

; Arguments: RCX, RDX, R8, R9, then stack
; Shadow space: 32 bytes reserved on stack
; Return: RAX

; Example: func(a, b, c, d, e)
sub rsp, 0x28      ; Shadow space + alignment
mov rcx, [a]       ; 1st arg
mov rdx, [b]       ; 2nd arg
mov r8, [c]        ; 3rd arg
mov r9, [d]        ; 4th arg
mov [rsp+0x20], [e] ; 5th arg on stack
call func
add rsp, 0x28

ARM Assembly Patterns

ARM64 (AArch64) Calling Convention

; Arguments: X0-X7
; Return: X0 (and X1 for 128-bit)
; Frame pointer: X29
; Link register: X30

; Function prologue
stp x29, x30, [sp, #-16]!  ; Save FP and LR
mov x29, sp                 ; Set frame pointer

; Function epilogue
ldp x29, x30, [sp], #16    ; Restore FP and LR
ret

; Arguments: R0-R3, then stack
; Return: R0 (and R1 for 64-bit)
; Link register: LR (R14)

; Function prologue
push {fp, lr}
add fp, sp, #4

; Function epilogue
pop {fp, pc}    ; Return by popping PC

; if (a == b)
cmp eax, ebx
jne skip_block
; ... if body ...
skip_block:

; if (a < b) - signed
cmp eax, ebx
jge skip_block    ; Jump if greater or equal
; ... if body ...
skip_block:

; if (a < b) - unsigned
cmp eax, ebx
jae skip_block    ; Jump if above or equal
; ... if body ...
skip_block:

; for (int i = 0; i < n; i++)
xor ecx, ecx           ; i = 0
loop_start:
cmp ecx, [n]           ; i < n
jge loop_end
; ... loop body ...
inc ecx                ; i++
jmp loop_start
loop_end:

; while (condition)
jmp loop_check
loop_body:
; ... body ...
loop_check:
cmp eax, ebx
jl loop_body

; do-while
loop_body:
; ... body ...
cmp eax, ebx
jl loop_body

; Jump table pattern
mov eax, [switch_var]
cmp eax, max_case
ja default_case
jmp [jump_table + eax*8]

; Sequential comparison (small switch)
cmp eax, 1
je case_1
cmp eax, 2
je case_2
cmp eax, 3
je case_3
jmp default_case

; array[i] - 4-byte elements
mov eax, [rbx + rcx*4]        ; rbx=base, rcx=index

; array[i] - 8-byte elements
mov rax, [rbx + rcx*8]

; Multi-dimensional array[i][j]
; arr[i][j] = base + (i * cols + j) * element_size
imul eax, [cols]
add eax, [j]
mov edx, [rbx + rax*4]

struct Example {
    int a;      // offset 0
    char b;     // offset 4
    // padding  // offset 5-7
    long c;     // offset 8
    short d;    // offset 16
};

; Accessing struct fields
mov rdi, [struct_ptr]
mov eax, [rdi]         ; s->a (offset 0)
movzx eax, byte [rdi+4] ; s->b (offset 4)
mov rax, [rdi+8]       ; s->c (offset 8)
movzx eax, word [rdi+16] ; s->d (offset 16)

; while (node != NULL)
list_loop:
test rdi, rdi          ; node == NULL?
jz list_done
; ... process node ...
mov rdi, [rdi+8]       ; node = node->next (assuming next at offset 8)
jmp list_loop
list_done:

; strlen pattern
xor ecx, ecx
strlen_loop:
cmp byte [rdi + rcx], 0
je strlen_done
inc ecx
jmp strlen_loop
strlen_done:
; ecx contains length

; strcpy pattern
strcpy_loop:
mov al, [rsi]
mov [rdi], al
test al, al
jz strcpy_done
inc rsi
inc rdi
jmp strcpy_loop
strcpy_done:

; memcpy using rep movsb
mov rdi, dest
mov rsi, src
mov rcx, count
rep movsb

; Multiplication by constant
; x * 3
lea eax, [rax + rax*2]

; x * 5
lea eax, [rax + rax*4]

; x * 10
lea eax, [rax + rax*4]  ; x * 5
add eax, eax            ; * 2

; Division by power of 2 (signed)
mov eax, [x]
cdq                     ; Sign extend to EDX:EAX
and edx, 7              ; For divide by 8
add eax, edx            ; Adjust for negative
sar eax, 3              ; Arithmetic shift right

; Modulo power of 2
and eax, 7              ; x % 8

; Test specific bit
test eax, 0x80          ; Test bit 7
jnz bit_set

; Set bit
or eax, 0x10            ; Set bit 4

; Clear bit
and eax, ~0x10          ; Clear bit 4

; Toggle bit
xor eax, 0x10           ; Toggle bit 4

; Count leading zeros
bsr eax, ecx            ; Bit scan reverse
xor eax, 31             ; Convert to leading zeros

; Population count (popcnt)
popcnt eax, ecx         ; Count set bits

; Local variable at rbp-8
mov qword [rbp-8], rax  ; Store to local
mov rax, [rbp-8]        ; Load from local

; Stack-allocated array
lea rax, [rbp-0x40]     ; Array starts at rbp-0x40
mov [rax], edx          ; array[0] = value
mov [rax+4], ecx        ; array[1] = value

; Identify parameters by register usage
func:
    ; rdi used as first param (System V)
    mov [rbp-8], rdi    ; Save param to local
    ; rsi used as second param
    mov [rbp-16], rsi
    ; Identify return by RAX at end
    mov rax, [result]
    ret

; 1-byte operations suggest char/bool
movzx eax, byte [rdi]   ; Zero-extend byte
movsx eax, byte [rdi]   ; Sign-extend byte

; 2-byte operations suggest short
movzx eax, word [rdi]
movsx eax, word [rdi]

; 4-byte operations suggest int/float
mov eax, [rdi]
movss xmm0, [rdi]       ; Float

; 8-byte operations suggest long/double/pointer
mov rax, [rdi]
movsd xmm0, [rdi]       ; Double

// In Ghidra scripting
// Fix function signature
Function func = getFunctionAt(toAddr(0x401000));
func.setReturnType(IntegerDataType.dataType, SourceType.USER_DEFINED);

// Create structure type
StructureDataType struct = new StructureDataType("MyStruct", 0);
struct.add(IntegerDataType.dataType, "field_a", null);
struct.add(PointerDataType.dataType, "next", null);

// Apply to memory
createData(toAddr(0x601000), struct);

# Find all calls to dangerous functions
for func in currentProgram.getFunctionManager().getFunctions(True):
    for ref in getReferencesTo(func.getEntryPoint()):
        if func.getName() in ["strcpy", "sprintf", "gets"]:
            print(f"Dangerous call at {ref.getFromAddress()}")

import idaapi
import idautils
import idc

# Find all function calls
def find_calls(func_name):
    for func_ea in idautils.Functions():
        for head in idautils.Heads(func_ea, idc.find_func_end(func_ea)):
            if idc.print_insn_mnem(head) == "call":
                target = idc.get_operand_value(head, 0)
                if idc.get_func_name(target) == func_name:
                    print(f"Call to {func_name} at {hex(head)}")

# Rename functions based on strings
def auto_rename():
    for s in idautils.Strings():
        for xref in idautils.XrefsTo(s.ea):
            func = idaapi.get_func(xref.frm)
            if func and "sub_" in idc.get_func_name(func.start_ea):
                # Use string as hint for naming
                pass

Anti-Pattern	Why It Fails	Correct Approach
Executing binary before static analysis	Destroys forensic state; safety risk	Map entry points and control flow statically first
Trusting decompiler output verbatim	Decompilers introduce artifacts and errors	Cross-reference with raw disassembly for critical paths
Assuming linear code flow	Misses indirect jumps, vtables, JIT paths	Check all xrefs and jump tables before tracing
Skipping architecture documentation	Wrong calling convention invalidates all analysis	Document arch + ABI before starting any analysis
Treating static inferences as confirmed	Inferences can be wrong without dynamic validation	Mark as [STATIC-ONLY] until runtime trace confirms