Go's dependency management embeds module paths and version strings in the binary. Extracting these reveals the malware's third-party dependencies (HTTP libraries, encryption packages, C2 frameworks), which provides insight into capabilities without full reverse engineering.
"""Analyze Go binary metadata for malware analysis."""
import struct
import sys
import re
def find_go_build_info(data):
"""Extract Go build information from binary."""
magic = b'\xff Go buildinf:'
offset = data.find(magic)
if offset == -1:
return None
print(f"[+] Go build info at offset 0x{offset:x}")
go_version = re.search(rb'go\d+\.\d+(?:\.\d+)?', data[offset:offset+256])
if go_version:
print(f" Go Version: {go_version.group().decode()}")
return offset
def find_pclntab(data):
"""Locate the pclntab (PC Line Table) structure."""
magics = {
b'\xfb\xff\xff\xff\x00\x00': "Go 1.2-1.15",
b'\xfa\xff\xff\xff\x00\x00': "Go 1.16-1.17",
b'\xf1\xff\xff\xff\x00\x00': "Go 1.18-1.19",
b'\xf0\xff\xff\xff\x00\x00': "Go 1.20+",
}
for magic, version in magics.items():
offset = data.find(magic)
if offset != -1:
print(f"[+] pclntab found at 0x{offset:x} ({version})")
return offset, version
return None, None
def extract_function_names(data, pclntab_offset):
"""Extract function names from pclntab."""
if pclntab_offset is None:
return []
functions = []
func_pattern = re.compile(
rb'(?:main|runtime|fmt|net|os|crypto|encoding|io|sync|'
rb'syscall|reflect|strings|bytes|path|time|math|sort|'
rb'github\.com|golang\.org)[/\.][\w/.]+',
)
for match in func_pattern.finditer(data):
name = match.group().decode('utf-8', errors='replace')
if len(name) > 4 and len(name) < 200:
functions.append(name)
return sorted(set(functions))
def extract_go_strings(data):
"""Extract Go-style strings (pointer+length pairs)."""
strings = []
ascii_pattern = re.compile(rb'[\x20-\x7e]{10,}')
for match in ascii_pattern.finditer(data):
s = match.group().decode('ascii')
interesting = [
'http', 'https', 'tcp', 'udp', 'dns',
'cmd', 'shell', 'exec', 'upload', 'download',
'encrypt', 'decrypt', 'key', 'token', 'password',
'c2', 'beacon', 'agent', 'implant', 'bot',
'mutex', 'persist', 'registry', 'scheduled',
]
if any(kw in s.lower() for kw in interesting):
strings.append(s)
return strings
def extract_dependencies(data):
"""Extract Go module dependencies from binary."""
deps = []
dep_pattern = re.compile(
rb'((?:github\.com|gitlab\.com|golang\.org|gopkg\.in|'
rb'go\.etcd\.io|google\.golang\.org)/[^\x00\s]{5,80})'
)
for match in dep_pattern.finditer(data):
dep = match.group().decode('utf-8', errors='replace')
deps.append(dep)
unique_deps = sorted(set(deps))
return unique_deps
def analyze_go_binary(filepath):
"""Full analysis of Go malware binary."""
with open(filepath, 'rb') as f:
data = f.read()
print(f"[+] Analyzing Go binary: {filepath}")
print(f" File size: {len(data):,} bytes")
print("=" * 60)
find_go_build_info(data)
pclntab_offset, go_version = find_pclntab(data)
functions = extract_function_names(data, pclntab_offset)
print(f"\n[+] Recovered {len(functions)} function names")
categories = {
"network": [], "crypto": [], "os_exec": [],
"file_io": [], "main": [], "third_party": [],
}
for f in functions:
if 'net/' in f or 'http' in f.lower():
categories["network"].append(f)
elif 'crypto' in f:
categories["crypto"].append(f)
elif 'os/exec' in f or 'syscall' in f:
categories["os_exec"].append(f)
elif 'os.' in f or 'io/' in f:
categories["file_io"].append(f)
elif f.startswith('main.'):
categories["main"].append(f)
elif 'github.com' in f or 'golang.org' in f:
categories["third_party"].append(f)
for cat, funcs in categories.items():
if funcs:
print(f"\n [{cat}] ({len(funcs)} functions):")
for fn in funcs[:10]:
print(f" {fn}")
deps = extract_dependencies(data)
print(f"\n[+] Dependencies ({len(deps)}):")
for dep in deps[:20]:
print(f" {dep}")
sus_strings = extract_go_strings(data)
print(f"\n[+] Suspicious strings ({len(sus_strings)}):")
for s in sus_strings[:20]:
print(f" {s}")
if __name__ == "__main__":
if len(sys.argv) < 2:
print(f"Usage: {sys.argv[0]} <go_binary>")
sys.exit(1)
analyze_go_binary(sys.argv[1])
def analyze_go_binary_ghidra():
"""Ghidra script for Go binary analysis."""
from ghidra.program.model.mem import MemoryAccessException
program = getCurrentProgram()
memory = program.getMemory()
listing = program.getListing()
print("[+] Go Binary Analysis Script")
print(f" Program: {program.getName()}")
pclntab_magics = [
bytes([0xf0, 0xff, 0xff, 0xff]),
bytes([0xf1, 0xff, 0xff, 0xff]),
bytes([0xfa, 0xff, 0xff, 0xff]),
bytes([0xfb, 0xff, 0xff, 0xff]),
]
for magic in pclntab_magics:
addr = memory.findBytes(
program.getMinAddress(), magic, None, True, None
)
if addr:
print(f"[+] pclntab found at {addr}")
program.getSymbolTable().createLabel(
addr, "go_pclntab", None,
ghidra.program.model.symbol.SourceType.ANALYSIS
)
break
print("[+] Fixing Go string references...")
symbol_table = program.getSymbolTable()
func_count = 0
for symbol in symbol_table.getAllSymbols(True):
name = symbol.getName()
if ('.' in name and
any(pkg in name for pkg in
['main.', 'runtime.', 'net.', 'crypto.', 'os.'])):
func_count += 1
print(f"[+] Found {func_count} Go function symbols")
analyze_go_binary_ghidra()
