def MacroHunter(targetFile):
answerTable = PrettyTable()
answerTable.field_names = [f"{green}Threat Levels{white}", f"{green}Macros{white}", f"{green}Descriptions{white}"]
print(f"\n{infoS} Looking for VBA Macros...")
try:
fileData = open(targetFile, "rb").read()
vbaparser = VBA_Parser(targetFile, fileData)
macroList = list(vbaparser.analyze_macros())
if vbaparser.contains_macros == True:
for fi in range(0, len(macroList)):
if macroList[fi][0] == 'Suspicious':
if "(use option --deobf to deobfuscate)" in macroList[fi][2]:
sanitized = f"{macroList[fi][2]}".replace("(use option --deobf to deobfuscate)", "")
answerTable.add_row([f"{yellow}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{sanitized}"])
elif "(option --decode to see all)" in macroList[fi][2]:
sanitized = f"{macroList[fi][2]}".replace("(option --decode to see all)", "")
answerTable.add_row([f"{yellow}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{sanitized}"])
else:
answerTable.add_row([f"{yellow}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
elif macroList[fi][0] == 'IOC':
answerTable.add_row([f"{magenta}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
elif macroList[fi][0] == 'AutoExec':
answerTable.add_row([f"{red}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
else:
answerTable.add_row([f"{macroList[fi][0]}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
print(f"{answerTable}\n")
else:
print(f"{errorS} Not any VBA macros found.")
except:
print(f"{errorS} An error occured while parsing that file for macro scan.")
def doc_parsing(self, filename, filecontent):
'''
Function to parse the given data in mail content
'''
mil_attach = '' # reset var
# send data to vba parser
vbaparser = VBA_Parser(filename, data=filecontent)
# if a macro is detected
if vbaparser.detect_vba_macros():
results = vbaparser.analyze_macros()
nr = 1
self.log("VBA Macros found")
# generate report for log file
for kw_type, keyword, description in results:
if kw_type == 'Suspicious':
mil_attach += 'Macro Number %i:\n Type: %s\n Keyword: %s\n Description: %s\n' % (nr, kw_type, keyword, description)
nr += 1
mil_attach += '\nSummery:\nAutoExec keywords: %d\n' % vbaparser.nb_autoexec
mil_attach += 'Suspicious keywords: %d\n' % vbaparser.nb_suspicious
mil_attach += 'IOCs: %d\n' % vbaparser.nb_iocs
mil_attach += 'Hex obfuscated strings: %d\n' % vbaparser.nb_hexstrings
mil_attach += 'Base64 obfuscated strings: %d\n' % vbaparser.nb_base64strings
mil_attach += 'Dridex obfuscated strings: %d\n' % vbaparser.nb_dridexstrings
mil_attach += 'VBA obfuscated strings: %d' % vbaparser.nb_vbastrings
r_level = vbaparser.nb_autoexec + vbaparser.nb_suspicious + vbaparser.nb_iocs + vbaparser.nb_hexstrings + vbaparser.nb_base64strings + vbaparser.nb_dridexstrings + vbaparser.nb_vbastrings
# set reject level to global
self.level = r_level
vbaparser.close()
return mil_attach # return the log to caller
else:
self.log("VBA no Macros found in file")
vbaparser.close()
return None # nothing found
def parseOLEDocument(f):
"""Parse an OLE document for VBA macros"""
if not f or not useOLETools:
return
writeLog('DEBUG: Analyzing with oletools')
try:
v = VBA_Parser(f)
except:
writeLog("Not a supported file format: %s" % f)
return
writeLog('DEBUG: Detected file type: %s' % v.type)
if v.detect_vba_macros():
writeLog('DEBUG: VBA Macros found')
try:
t = open("%s.analysis" % f, 'w')
except IOError as e:
writeLog("Cannot create analysis file %s.analysis: %s" % (f,e.strerror))
return
for kw_type, keyword, description in v.analyze_macros():
t.write("%-12s | %-25s | %s\n" % (kw_type, keyword, description))
t.close()
writeLog("DEBUG: Analysis dumped to %s.analysis" % f)
else:
writeLog('DEBUG: No VBA Macros found')
return
def parseOLEDocument(f):
"""Parse an OLE document for VBA macros"""
if not f or not useOLETools:
return
writeLog('DEBUG: Analyzing with oletools')
try:
v = VBA_Parser(f)
except:
writeLog("Not a supported file format: %s" % f)
return
writeLog('DEBUG: Detected file type: %s' % v.type)
# Hack: Search for a .js extension
fname, fextension = os.path.splitext(f)
if v.detect_vba_macros() or fextension == ".js":
writeLog('DEBUG: VBA Macros/JScript found')
try:
t = open("%s.analysis" % f, 'w')
except IOError as e:
writeLog("Cannot create analysis file %s.analysis: %s" % (f,e.strerror))
return
for kw_type, keyword, description in v.analyze_macros():
t.write("%-12s | %-25s | %s\n" % (kw_type, keyword, description))
t.close()
writeLog("DEBUG: Analysis dumped to %s.analysis" % f)
else:
writeLog('DEBUG: No VBA Macros found')
return
def olevba_trig(file):
try:
vbaparser = VBA_Parser(file)
if vbaparser.detect_vba_macros():
for (filename, stream_path, vba_filename,
vba_code) in vbaparser.extract_macros():
print('Filename :', filename)
print('OLE stream :', stream_path)
print('VBA filename:', vba_filename)
print('- ' * 39)
print(vba_code)
print('- ' * 39)
results = vbaparser.analyze_macros()
for kw_type, keyword, description in results:
print('type=%s - keyword=%s - description=%s' %
(kw_type, keyword, description))
print('AutoExec keywords: %d' % vbaparser.nb_autoexec)
print('Suspicious keywords: %d' % vbaparser.nb_suspicious)
print('IOCs: %d' % vbaparser.nb_iocs)
print('Hex obfuscated strings: %d' % vbaparser.nb_hexstrings)
print('Base64 obfuscated strings: %d' %
vbaparser.nb_base64strings)
print('Dridex obfuscated strings: %d' %
vbaparser.nb_dridexstrings)
print('VBA obfuscated strings: %d' % vbaparser.nb_vbastrings)
print("\n")
except:
e = sys.exc_info()[0]
print(f'{e} from {file}')
def get_macros():
extracted_macros = []
macro_analysis = []
tags = []
try:
vbaparser = VBA_Parser('/sample')
vbaparser.detect_vba_macros()
for (filename, stream_path, vba_filename,
vba_code) in vbaparser.extract_macros():
extracted_macros.append({
"stream_path": stream_path,
"vba_filename": vba_filename,
"vba_code": vba_code
})
try:
for kw_type, keyword, description in vbaparser.analyze_macros():
macro_analysis.append({
"kw_type": kw_type,
"keyword": keyword,
"description": description
})
if keyword == 'Shell':
tags.append('run-file')
except TypeError:
pass
macro_suspicious_categories = {
"nb_macros": vbaparser.nb_macros,
"nb_autoexec": vbaparser.nb_autoexec,
"nb_suspicious": vbaparser.nb_suspicious,
"nb_iocs": vbaparser.nb_iocs,
"nb_hexstrings": vbaparser.nb_hexstrings,
"nb_base64strings": vbaparser.nb_base64strings,
"nb_dridexstrings": vbaparser.nb_dridexstrings,
"nb_vbastrings": vbaparser.nb_vbastrings,
}
if vbaparser.nb_macros:
tags.append('macros')
if vbaparser.nb_hexstrings or vbaparser.nb_base64strings:
tags.append('obfuscated')
except FileOpenError:
return None, tags
return {
"extracted_macros": extracted_macros,
"macro_analysis": macro_analysis,
"macro_suspicious_categories": macro_suspicious_categories
}, tags
def vbaparsing(filename):
vbafile = VBA_Parser(filename)
results = ""
for (filename, stream_path, vba_filename,
vba_code) in vbafile.extract_macros():
results = results + vba_code
result = vbafile.analyze_macros()
for kw_type, keyword, description in result:
results = results + 'type=%s - keyword=%s - description=%s' % (
kw_type, keyword, description)
return results
def get_macros_infos(self):
"""Check file macroses for suspisious behaviour."""
if not self.has_macros:
return None
vbaparser = VBA_Parser(self.file_path)
vbaparser.analyze_macros()
# obfuscated vba and autoexec danger
autoexec_and_vba = 0
if vbaparser.nb_autoexec > 0 and vbaparser.nb_vbastrings > 0:
autoexec_and_vba = vbaparser.nb_vbastrings
# obfuscated Base64 and autoexec danger
autoexec_and_base64 = 0
if vbaparser.nb_autoexec > 0 and vbaparser.nb_base64strings > 0:
autoexec_and_base64 = vbaparser.nb_base64strings
# obfuscated HEX and autoexec danger
autoexec_and_HEX = 0
if vbaparser.nb_autoexec > 0 and vbaparser.nb_hexstrings > 0:
autoexec_and_HEX = vbaparser.nb_hexstrings
macros_infos = [
{'number': vbaparser.nb_autoexec,
'description': 'Ключевые слова автоматического вызова', 'danger': False, 'function': olevba.detect_autoexec},
{'number': autoexec_and_HEX,
'description': 'Автоматический вызов шеснадцатиричных обфусцированных строк', 'danger': False, 'function': olevba.detect_hex_strings},
{'number': vbaparser.nb_vbastrings,
'description': 'VBA обфусцированные строки', 'danger': False, 'function': olevba.detect_vba_strings},
{'number': vbaparser.nb_suspicious,
'description': 'Подозрительные ключевые слова', 'danger': False, 'function': olevba.detect_suspicious},
{'number': autoexec_and_vba,
'description': 'Автоматический вызов обфусцированного кода', 'danger': True, 'function': olevba.detect_vba_strings},
{'number': vbaparser.nb_dridexstrings,
'description': 'Dridex обфусцированные строки', 'danger': True, 'function': olevba.detect_dridex_strings},
{'number': autoexec_and_base64,
'description': 'Автоматический вызов Base64 обфусцированных строк', 'danger': True, 'function': olevba.detect_base64_strings},
]
vbaparser.close()
return macros_infos
def check_macros(doc_path, filename) -> dict:
try:
vbaparser = VBA_Parser(doc_path)
if not vbaparser.detect_vba_macros():
return ""
logging.warning("VBA macros in \"%s\"" % filename)
details = "Macro Results\n"
suspicious_count = 0
suspicious_list = []
ioc_list = []
ioc_count = 0
mal_score = 0
logging.disable(level=logging.CRITICAL)
results = vbaparser.analyze_macros()
logging.disable(level=logging.NOTSET)
for kw_type, keyword, description in results:
details += "\t - " + kw_type + " - (" + keyword + ") - " + description + "\n"
if kw_type.lower() == "suspicious":
suspicious_count += 1
suspicious_list.append(keyword)
elif kw_type.lower() == "ioc":
ioc_count += 1
ioc_list.append(keyword)
if suspicious_count != 0:
logging.warning("Found %d suspicious items in \"%s\"" %
(suspicious_count, filename))
mal_score += suspicious_count
if ioc_count != 0:
logging.warning("Found %d IOCs: %s, in \"%s\"" %
(ioc_count, ioc_list, filename))
mal_score += ioc_count * 2
return {'details': details, 'mal_score': mal_score}
except Exception as e:
logging.error("Failed to parse macros for: {} - {}".format(
filename, e))
return
def _ole_analysis(full_targ_path):
# This function calls a number of tools / scripts to run against document samples containing OLE data and extracts data and/or performs analysis as needed.
try:
vba_parse_Obj = VBA_Parser(full_targ_path)
except AttributeError:
return ("ERROR_PARSING", "ERROR_PARSING", "ERROR_PARSING",
"ERROR_PARSING")
macro_analysis_over = []
macro_analysis_info = []
if vba_parse_Obj.detect_vba_macros():
vba_macro = "Present"
# Utilizing oletools to perform analysis.
# Grabbing info from each macro.
MA_CNT = 1
for (file_name, ole_stream, vba_filename,
vba_code) in vba_parse_Obj.extract_macros():
macro_analysis_over.append(str(MA_CNT) + ':' + str(full_targ_path))
macro_analysis_over.append(
str(MA_CNT) + ":Filename :" + file_name)
macro_analysis_over.append(
str(MA_CNT) + ":OLE Stream :" + ole_stream)
macro_analysis_over.append(
str(MA_CNT) + ":VBA Filename :" + vba_filename)
macro_analysis_over.append(str(MA_CNT) + ':' + vba_code)
MA_CNT += 1
# Grabbing some overall VBA analysis info.
macro_flag_types = []
macro_analysis_res = vba_parse_Obj.analyze_macros()
if isinstance(macro_analysis_res, list):
for iocType in macro_analysis_res:
if str(iocType) not in macro_flag_types:
macro_flag_types.append(str(iocType[0]))
if len(macro_flag_types) > 0:
iocs = ':'.join(list(set(macro_flag_types)))
else:
iocs = "None"
else:
vba_macro = "None"
iocs = "None"
macro_analysis_res = "None"
vba_parse_Obj.close()
return (vba_macro, macro_analysis_over, str(macro_analysis_res), iocs)
def _run(self, scanObject, result, depth, args):
moduleResult = []
vbap_buffer = VBA_Parser(scanObject.buffer)
try:
if vbap_buffer.detect_vba_macros():
vbap_result = vbap_buffer.analyze_macros()
for kw_type, keyword, description in vbap_result:
kw = '%s - %s' % ( keyword,description )
scanObject.addMetadata(self.module_name,kw_type,kw)
except (QuitScanException, GlobalScanTimeoutError, GlobalModuleTimeoutError):
raise
except:
logging.debug("Failed to parse OLEVBA")
vbap_buffer.close()
return moduleResult
def _ole_analysis(full_targ_path):
# This function calls a number of tools / scripts to run against document samples containing OLE data and extracts data and/or performs analysis as needed.
try:
vba_parse_Obj = VBA_Parser(full_targ_path)
except AttributeError:
return("ERROR_PARSING", "ERROR_PARSING", "ERROR_PARSING", "ERROR_PARSING")
macro_analysis_over = []
macro_analysis_info = []
if vba_parse_Obj.detect_vba_macros():
vba_macro = "Present"
# Utilizing oletools to perform analysis.
# Grabbing info from each macro.
MA_CNT = 1
for (file_name, ole_stream, vba_filename, vba_code) in vba_parse_Obj.extract_macros():
macro_analysis_over.append(str(MA_CNT)+':'+str(full_targ_path))
macro_analysis_over.append(str(MA_CNT)+":Filename :"+file_name)
macro_analysis_over.append(str(MA_CNT)+":OLE Stream :"+ole_stream)
macro_analysis_over.append(str(MA_CNT)+":VBA Filename :"+vba_filename)
macro_analysis_over.append(str(MA_CNT)+':'+vba_code)
MA_CNT+=1
# Grabbing some overall VBA analysis info.
macro_flag_types = []
macro_analysis_res = vba_parse_Obj.analyze_macros()
if isinstance(macro_analysis_res, list):
for iocType in macro_analysis_res:
if str(iocType) not in macro_flag_types:
macro_flag_types.append(str(iocType[0]))
if len(macro_flag_types) > 0:
iocs = ':'.join(list(set(macro_flag_types)))
else:
iocs = "None"
else:
vba_macro = "None"
iocs = "None"
macro_analysis_res = "None"
vba_parse_Obj.close()
return(vba_macro, macro_analysis_over, str(macro_analysis_res), iocs)
def MacroHunter(targetFile):
answerTable = PrettyTable()
answerTable.field_names = [f"{green}Threat Levels{white}", f"{green}Macros{white}", f"{green}Descriptions{white}"]
print(f"\n{infoS} Looking for VBA Macros...")
fileData = open(targetFile, "rb").read()
vbaparser = VBA_Parser(targetFile, data=fileData)
if vbaparser.contains_macros == True:
macroList = list(vbaparser.analyze_macros())
for fi in range(0, len(macroList)):
if macroList[fi][0] == 'Suspicious':
answerTable.add_row([f"{yellow}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
elif macroList[fi][0] == 'IOC':
answerTable.add_row([f"{magenta}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
elif macroList[fi][0] == 'AutoExec':
answerTable.add_row([f"{red}{macroList[fi][0]}{white}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
else:
answerTable.add_row([f"{macroList[fi][0]}", f"{macroList[fi][1]}", f"{macroList[fi][2]}"])
print(f"{answerTable}\n")
else:
print(f"{errorS} Not any macros found.")
def detect(self, filename):
return_list = []
vbaparser = VBA_Parser(filename)
if vbaparser.detect_vba_macros():
for (filename, stream_path, vba_filename,
vba_code) in vbaparser.extract_macros():
return_list.append({
'filename': filename,
'ole_stream': stream_path,
'vba_filename': vba_filename,
'vba_code': vba_code
})
results = vbaparser.analyze_macros()
for kw_type, keyword, description in results:
return_list.append({
'type': kw_type,
'keyword': keyword,
'description': description
})
return_list.append({'revealed_macro': vbaparser.reveal()})
return return_list
else:
return None
def inspect_vba_data(self, filename, filecontent):
'''
Function to parse the given data in mail content
'''
vbaparser_report_log = '' # reset var
# send data to vba parser
vbaparser = VBA_Parser(filename, data=filecontent)
# if a macro is detected
if not vbaparser.detect_vba_macros():
self.log("VBA no Macros found in file")
vbaparser.close()
return None # nothing found
else:
results = vbaparser.analyze_macros()
nr = 1
self.log("VBA Macros found")
# generate report for log file
for kw_type, keyword, description in results:
if kw_type == 'Suspicious':
vbaparser_report_log += 'Macro Number %i:\n Type: %s\n Keyword: %s\n Description: %s\n' % (
nr, kw_type, keyword, description)
nr += 1
vbaparser_report_log += '\nSummery:\nAutoExec keywords: %d\n' % vbaparser.nb_autoexec
vbaparser_report_log += 'Suspicious keywords: %d\n' % vbaparser.nb_suspicious
vbaparser_report_log += 'IOCs: %d\n' % vbaparser.nb_iocs
vbaparser_report_log += 'Hex obfuscated strings: %d\n' % vbaparser.nb_hexstrings
vbaparser_report_log += 'Base64 obfuscated strings: %d\n' % vbaparser.nb_base64strings
vbaparser_report_log += 'Dridex obfuscated strings: %d\n' % vbaparser.nb_dridexstrings
vbaparser_report_log += 'VBA obfuscated strings: %d' % vbaparser.nb_vbastrings
# TBD: calculate a better level - add additional values to Base64 and Hex. No human writes such strings into code.
r_level = vbaparser.nb_autoexec + vbaparser.nb_suspicious + vbaparser.nb_iocs + vbaparser.nb_hexstrings + vbaparser.nb_base64strings + vbaparser.nb_dridexstrings + vbaparser.nb_vbastrings
# set reject level to global
#self.level = r_level
vbaparser.close()
return [r_level, vbaparser_report_log] # return the log to caller
def ProcessFile(path):
if not(os.path.isfile(path)):
print '{0} not a file!'.format(path)
return 2
try:
data = {}
data['valid'] = True
oledata = {}
vbaparser = VBA_Parser(path)
oledata['has_macros'] = vbaparser.detect_vba_macros()
# dump macros content
macros = []
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
macro = {}
macro['filename'] = filename
macro['stream'] = stream_path
macro['vba'] = vba_filename
macro['content'] = convert_to_printable_null_terminated(vba_code)
macros.append(macro)
oledata['macros'] = macros
# macro analysis
macros_warnings = []
results = vbaparser.analyze_macros()
for kw_type, keyword, description in results:
warning = {}
warning['type'] = kw_type
warning['keyword'] = keyword
warning['description'] = description
macros_warnings.append(warning)
oledata['macros_warnings'] = macros_warnings
# counters
counters = {}
counters['autoexec'] = vbaparser.nb_autoexec
counters['suspicious'] = vbaparser.nb_suspicious
counters['iocs'] = vbaparser.nb_iocs
counters['hexstrings'] = vbaparser.nb_hexstrings
counters['base64strings'] = vbaparser.nb_base64strings
counters['dridexstrings'] = vbaparser.nb_dridexstrings
counters['vbastrings'] = vbaparser.nb_vbastrings
oledata['counters'] = counters
# deobfuscation
oledata['deobfuscated'] = convert_to_printable_null_terminated(vbaparser.reveal())
# close
vbaparser.close()
data['data'] = oledata
encoded = json.dumps(data)
print encoded
except Exception as ex:
data = {}
data['valid'] = False
data['error'] = str(ex)
print json.dumps(data)
return 1
return 0
print ("- "*39)
print ("vba_code",vba_code)
vba_scanner = VBA_Scanner(vba_code)
results = vba_scanner.scan(include_decoded_strings=True)
for kw_type, keyword, description in results:
print ("type=%s - keyword=%s - description=%s" % (kw_type, keyword, description))
autoexec_keywords = detect_autoexec(vba_code)
if autoexec_keywords:
print("Auto-executable Macro keyword is detected. :")
for keyword, description in autoexec_keywords:
print("%s: %s' % (keyword, description)")
else:
print ("Auto-executable Macro keywords is not detected.")
results = vbaparser.analyze_macros()
for kw_type, keyword, description in results:
print ("type=%s - keyword=%s - description=%s" % (kw_type, keyword, description))
print ("AutoExec keywords: %d" % vbaparser.nb_autoexec)
print ("Suspicious keywords: %d" % vbaparser.nb_suspicious)
print ("IOCs: %d" % vbaparser.nb_iocs)
print ("Hex obfuscated strings: %d" % vbaparser.nb_hexstrings)
print ("Base64 obfuscated strings: %d" % vbaparser.nb_base64strings)
print ("Dridex obfuscated strings: %d" % vbaparser.nb_dridexstrings)
print ("VBA obfuscated strings: %d" % vbaparser.nb_vbastrings)
# 퍼져 닫기
vbaparser.close()
def parse_vba(file):
print_output(file, '\n\n-----------------------------------------\n[Analyzing with olevba]\n-----------------------------------------\n', 'text')
ole_macro_result = 'no vb-macro'
has_macros = False
indicators = []
macro_indicators = []
vbaparser = VBA_Parser(filescanner_proc_dir+file)
# Check for Macros
if not vbaparser.detect_vba_macros():
print_output(file, '[-] No Macros Found', 'text')
return has_macros, ole_macro_result, indicators
if True:
print_output(file, '[-] MACROS FOUND', 'text')
has_macros = True
ole_macro_result = 'VB-MACRO FOUND'
# Variable to be passed to MacroRaptor
vba_code_all_modules = ''
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_all_macros():
vba_code_all_modules += vba_code + '\n'
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
print_output(file, '\nOLE Stream: {0}'.format(string_clean(stream_path)), 'text')
print_output(file, 'VBA Filename: {0}'.format(string_clean(vba_filename)), 'text')
# Analyse the VBA Code
results = vbaparser.analyze_macros(show_decoded_strings=True)
for kw_type, keyword, description in results:
# Add IOC detections to indicators list
if kw_type == 'IOC':
indicators.append(description+': '+keyword)
print_output(file, '{} - {} - {}'.format(kw_type, keyword, description), 'shell')
else:
print_output(file, '{} - {} - {}'.format(kw_type, keyword, description), 'text')
# Deobfusgate and return macro code
# print_output(file, '\n'+vbaparser.reveal(), 'text')
# Print number of items in each category and append to indicators list
print_output(file, '', 'shell')
print_output(file, 'AutoExec keywords: {}'.format(vbaparser.nb_autoexec), 'shell')
if vbaparser.nb_autoexec != 0:
indicators.append('AutoExec keywords: {}'.format(vbaparser.nb_autoexec))
print_output(file, 'Suspicious keywords: {}'.format(vbaparser.nb_suspicious), 'shell')
if vbaparser.nb_suspicious != 0:
indicators.append('Suspicious keywords: {}'.format(vbaparser.nb_suspicious))
print_output(file, 'IOCs: {}'.format(vbaparser.nb_iocs), 'shell')
print_output(file, 'Hex obfuscated strings: {}'.format(vbaparser.nb_hexstrings), 'shell')
if vbaparser.nb_hexstrings != 0:
indicators.append('Hex obfuscated strings: {}'.format(vbaparser.nb_hexstrings))
print_output(file, 'Base64 obfuscated strings: {}'.format(vbaparser.nb_base64strings), 'shell')
if vbaparser.nb_base64strings != 0:
indicators.append('Base64 obfuscated strings: {}'.format(vbaparser.nb_base64strings))
print_output(file, 'Dridex obfuscated strings: {}'.format(vbaparser.nb_dridexstrings), 'shell')
if vbaparser.nb_dridexstrings != 0:
indicators.append('Dridex obfuscated strings: {}'.format(vbaparser.nb_dridexstrings))
print_output(file, 'VBA obfuscated strings: {}'.format(vbaparser.nb_vbastrings), 'shell')
if vbaparser.nb_vbastrings != 0:
indicators.append('VBA obfuscated strings: {}'.format(vbaparser.nb_vbastrings))
# Update indicators list with matches from MRaptor
macro_indicators = scan_macro(file, vba_code_all_modules)
indicators = indicators + macro_indicators
# Use oledump to gather VBA code for archiving
oledump_scan(file, '-p plugin_vba_summary.py')
# Close the file
vbaparser.close()
return has_macros, ole_macro_result, indicators
sus_filedata = open(sus_file, 'rb').read() vbaparser = VBA_Parser(sus_file, data=sus_filedata) ## Manual Macro extraction details ##for (sys.argv[1], stream_path, vba_filename, vba_code) in vbaparser.extract_macros(): ## print '-' * 79 ## print 'Filename :', sys.argv[1] ## print 'OLE stream :', stream_path ## print 'VBA filename :', vba_filename ## print '- ' * 39 ## print vba_code # Macros analysis global results results = vbaparser.analyze_macros() def show_message_macro_analysis(): print ' ' * 40 + '===============' print ' ' * 40 + 'Macros analysis' print ' ' * 40 + '===============\n\n' def show_message_keywords(): print ' Type\t\tKeyword\t\t Description' print '==========\t==========\t\t=========================================================' for kw_type, keyword, description in results: print '%s\t%s\t\t\t%s'% (kw_type, keyword, description) print '\n\n' def show_message_indicators(): print '=' * 35 print 'AutoExec keywords: %d' % vbaparser.nb_autoexec
class DocInfo(FileAnalyzer):
def set_config(self, additional_config_params):
self.olevba_results = {}
self.vbaparser = None
self.experimental = additional_config_params.get("experimental", False)
self.passwords_to_check = []
# this is to extract the passwords for encryption requested by the client
# you can use pyintelowl to send additional passwords to check for
# example:
# "additional_configuration": {
# "Doc_Info_Experimental": {
# "additional_passwords_to_check": ["testpassword"]
# }
# },
additional_passwords_to_check = additional_config_params.get(
"additional_passwords_to_check", []
)
if isinstance(additional_passwords_to_check, list):
self.passwords_to_check.extend(additional_passwords_to_check)
def run(self):
results = {}
# olevba
try:
self.vbaparser = VBA_Parser(self.filepath)
self.manage_encrypted_doc()
if self.experimental:
self.experimental_analysis()
# go on with the normal oletools execution
self.olevba_results["macro_found"] = self.vbaparser.detect_vba_macros()
if self.olevba_results["macro_found"]:
vba_code_all_modules = ""
macro_data = []
for (
v_filename,
stream_path,
vba_filename,
vba_code,
) in self.vbaparser.extract_macros():
extracted_macro = {
"filename": v_filename,
"ole_stream": stream_path,
"vba_filename": vba_filename,
"vba_code": vba_code,
}
macro_data.append(extracted_macro)
vba_code_all_modules += vba_code + "\n"
self.olevba_results["macro_data"] = macro_data
# example output
#
# {'description': 'Runs when the Word document is opened',
# 'keyword': 'AutoOpen',
# 'type': 'AutoExec'},
# {'description': 'May run an executable file or a system command',
# 'keyword': 'Shell',
# 'type': 'Suspicious'},
# {'description': 'May run an executable file or a system command',
# 'keyword': 'WScript.Shell',
# 'type': 'Suspicious'},
# {'description': 'May run an executable file or a system command',
# 'keyword': 'Run',
# 'type': 'Suspicious'},
# {'description': 'May run PowerShell commands',
# 'keyword': 'powershell',
# 'type': 'Suspicious'},
# {'description': '9BA55BE5', 'keyword': 'xxx', 'type': 'Hex String'},
# mraptor
macro_raptor = mraptor.MacroRaptor(vba_code_all_modules)
if macro_raptor:
macro_raptor.scan()
results["mraptor"] = (
"suspicious" if macro_raptor.suspicious else "ok"
)
# analyze macros
analyzer_results = self.vbaparser.analyze_macros()
# it gives None if it does not find anything
if analyzer_results:
analyze_macro_results = []
for kw_type, keyword, description in analyzer_results:
if kw_type != "Hex String":
analyze_macro_result = {
"type": kw_type,
"keyword": keyword,
"description": description,
}
analyze_macro_results.append(analyze_macro_result)
self.olevba_results["analyze_macro"] = analyze_macro_results
except CannotDecryptException as e:
logger.info(e)
except Exception as e:
error_message = f"job_id {self.job_id} vba parser failed. Error: {e}"
logger.exception(error_message)
self.report["errors"].append(error_message)
finally:
if self.vbaparser:
self.vbaparser.close()
results["olevba"] = self.olevba_results
return results
def manage_encrypted_doc(self):
self.olevba_results["is_encrypted"] = False
# checks if it is an OLE file. That could be encrypted
if self.vbaparser.ole_file:
# check if the ole file is encrypted
is_encrypted = self.vbaparser.detect_is_encrypted()
self.olevba_results["is_encrypted"] = is_encrypted
# in the case the file is encrypted I try to decrypt it
# with the default password and the most common ones
if is_encrypted:
# by default oletools contains some basic passwords
# we just add some more guesses
common_pwd_to_check = []
for num in range(10):
common_pwd_to_check.append(f"{num}{num}{num}{num}")
# https://twitter.com/JohnLaTwC/status/1265377724522131457
filename_without_spaces_and_numbers = sub("[-_\d\s]", "", self.filename)
filename_without_extension = sub(
"(\..+)", "", filename_without_spaces_and_numbers
)
common_pwd_to_check.append(filename_without_extension)
self.passwords_to_check.extend(common_pwd_to_check)
decrypted_file_name = self.vbaparser.decrypt_file(
self.passwords_to_check
)
self.olevba_results[
"additional_passwords_tried"
] = self.passwords_to_check
if decrypted_file_name:
self.vbaparser = VBA_Parser(decrypted_file_name)
else:
self.olevba_results["cannot_decrypt"] = True
raise CannotDecryptException(
"cannot decrypt the file with the default password"
)
def experimental_analysis(self):
self.manage_xlm_macros()
def manage_xlm_macros(self):
self.olevba_results["xlm_macro"] = False
# check if the file contains an XLM macro
# and try an experimental parsing
# credits to https://twitter.com/gabriele_pippi for the idea
if self.vbaparser.detect_xlm_macros():
self.olevba_results["xlm_macro"] = True
logger.debug("experimental XLM macro analysis start")
parsed_file = b""
try:
excel_doc = XLSWrapper2(self.filepath)
ae_list = [
"auto_open",
"auto_close",
"auto_activate",
"auto_deactivate",
]
self.olevba_results["xlm_macro_autoexec"] = []
for ae in ae_list:
auto_exec_labels = excel_doc.get_defined_name(ae, full_match=False)
for label in auto_exec_labels:
self.olevba_results["xlm_macro_autoexec"].append(label[0])
for i in show_cells(excel_doc):
rec_str = ""
if len(i) == 5:
# rec_str = 'CELL:{:10}, {:20}, {}'
# .format(i[0].get_local_address(), i[2], i[4])
if i[2] != "None":
rec_str = "{:20}".format(i[2])
if rec_str:
parsed_file += rec_str.encode()
parsed_file += b"\n"
except Exception as e:
logger.info(f"experimental XLM macro analysis failed. Exception: {e}")
else:
logger.debug(
f"experimental XLM macro analysis succeded. "
f"Binary to analyze: {parsed_file}"
)
if parsed_file:
self.vbaparser = VBA_Parser(self.filename, data=parsed_file)
def run(self):
results = {}
# olevba
olevba_results = {}
try:
vbaparser = VBA_Parser(self.filepath)
olevba_results["macro_found"] = (
True if vbaparser.detect_vba_macros() else False
)
if olevba_results["macro_found"]:
macro_data = []
for (
v_filename,
stream_path,
vba_filename,
vba_code,
) in vbaparser.extract_macros():
extracted_macro = {
"filename": v_filename,
"ole_stream": stream_path,
"vba_filename": vba_filename,
"vba_code": vba_code,
}
macro_data.append(extracted_macro)
olevba_results["macro_data"] = macro_data
# example output
"""
{'description': 'Runs when the Word document is opened',
'keyword': 'AutoOpen',
'type': 'AutoExec'},
{'description': 'May run an executable file or a system command',
'keyword': 'Shell',
'type': 'Suspicious'},
{'description': 'May run an executable file or a system command',
'keyword': 'WScript.Shell',
'type': 'Suspicious'},
{'description': 'May run an executable file or a system command',
'keyword': 'Run',
'type': 'Suspicious'},
{'description': 'May run PowerShell commands',
'keyword': 'powershell',
'type': 'Suspicious'},
{'description': '9BA55BE5', 'keyword': 'xxx', 'type': 'Hex String'},
"""
analyzer_results = vbaparser.analyze_macros(show_decoded_strings=True)
# it gives None if it does not find anything
if analyzer_results:
analyze_macro_results = []
for kw_type, keyword, description in analyzer_results:
if kw_type != "Hex String":
analyze_macro_result = {
"type": kw_type,
"keyword": keyword,
"description": description,
}
analyze_macro_results.append(analyze_macro_result)
olevba_results["analyze_macro"] = analyze_macro_results
olevba_results["reveal"] = vbaparser.reveal()
vbaparser.close()
except Exception as e:
traceback.print_exc()
error_message = f"job_id {self.job_id} vba parser failed. Error: {e}"
logger.exception(error_message)
self.report["errors"].append(error_message)
results["olevba"] = olevba_results
# mraptor
macro_raptor = mraptor.MacroRaptor(olevba_results.get("reveal", None))
if macro_raptor:
macro_raptor.scan()
results["mraptor"] = "suspicious" if macro_raptor.suspicious else "ok"
return results
def run(analyzer_name, job_id, filepath, filename, md5,
additional_config_params):
logger.info("started analyzer {} job_id {}"
"".format(analyzer_name, job_id))
report = general.get_basic_report_template(analyzer_name)
try:
results = {}
# olevba
olevba_results = {}
try:
vbaparser = VBA_Parser(filepath)
olevba_results[
'macro_found'] = True if vbaparser.detect_vba_macros(
) else False
if olevba_results['macro_found']:
macro_data = []
for (v_filename, stream_path, vba_filename,
vba_code) in vbaparser.extract_macros():
extracted_macro = {
"filename": v_filename,
"ole_stream": stream_path,
"vba_filename": vba_filename,
"vba_code": vba_code
}
macro_data.append(extracted_macro)
olevba_results['macro_data'] = macro_data
# example output
'''
{'description': 'Runs when the Word document is opened',
'keyword': 'AutoOpen',
'type': 'AutoExec'},
{'description': 'May run an executable file or a system command',
'keyword': 'Shell',
'type': 'Suspicious'},
{'description': 'May run an executable file or a system command',
'keyword': 'WScript.Shell',
'type': 'Suspicious'},
{'description': 'May run an executable file or a system command',
'keyword': 'Run',
'type': 'Suspicious'},
{'description': 'May run PowerShell commands',
'keyword': 'powershell',
'type': 'Suspicious'},
{'description': '9BA55BE5', 'keyword': 'xxx', 'type': 'Hex String'},
'''
analyzer_results = vbaparser.analyze_macros(
show_decoded_strings=True)
# it gives None if it does not find anything
if analyzer_results:
analyze_macro_results = []
for kw_type, keyword, description in analyzer_results:
if kw_type != 'Hex String':
analyze_macro_result = {
"type": kw_type,
"keyword": keyword,
"description": description
}
analyze_macro_results.append(analyze_macro_result)
olevba_results['analyze_macro'] = analyze_macro_results
olevba_results['reveal'] = vbaparser.reveal()
vbaparser.close()
except Exception as e:
traceback.print_exc()
error_message = "job_id {} vba parser failed. Error: {}".format(
job_id, e)
logger.exception(error_message)
report['errors'].append(error_message)
results['olevba'] = olevba_results
# mraptor
macro_raptor = mraptor.MacroRaptor(olevba_results.get('reveal', ''))
if macro_raptor:
macro_raptor.scan()
results[
'mraptor'] = "suspicious" if macro_raptor.suspicious else 'ok'
# pprint.pprint(results)
report['report'] = results
except AnalyzerRunException as e:
error_message = "job_id:{} analyzer:{} md5:{} filename: {} Analyzer Error {}" \
"".format(job_id, analyzer_name, md5, filename, e)
logger.error(error_message)
report['errors'].append(error_message)
report['success'] = False
except Exception as e:
traceback.print_exc()
error_message = "job_id:{} analyzer:{} md5:{} filename: {} Unexpected Error {}" \
"".format(job_id, analyzer_name, md5, filename, e)
logger.exception(error_message)
report['errors'].append(str(e))
report['success'] = False
else:
report['success'] = True
general.set_report_and_cleanup(job_id, report, logger)
logger.info("ended analyzer {} job_id {}" "".format(analyzer_name, job_id))
return report
def collect_events(helper, ew):
if helper.get_arg('endpoint') == 'worldwide':
graph_url = 'https://graph.microsoft.com/v1.0'
elif helper.get_arg('endpoint') == 'gcchigh':
graph_url = 'https://graph.microsoft.us/v1.0'
access_token = _get_access_token(helper)
headers = {
"Authorization": "Bearer " + access_token,
"User-Agent": "MicrosoftGraphEmail-Splunk/" + _get_app_version(helper)
}
#"Prefer": "outlook.body-content-type=text"}
#defining email account to retrieve messages from
endpoint = "/users/" + helper.get_arg('audit_email_account')
#defining inbox id to retrieve messages from
endpoint += "/mailFolders/inbox/messages/"
#expanding property id 0x0E08 to gather message size, and then expanding attachments to get fileattachment type contentBytes
endpoint += "?$expand=SingleValueExtendedProperties($filter=Id eq 'LONG 0x0E08'),attachments"
#selecting which fields to retrieve from emails
endpoint += "&$select=receivedDateTime,subject,sender,from,hasAttachments,internetMessageId,toRecipients,ccRecipients,bccRecipients,replyTo,internetMessageHeaders,body,bodyPreview,isReadReceiptRequested,isDeliveryReceiptRequested"
#defining how many messages to retrieve from each page
endpoint += "&$top=980"
#getting the oldest messages first
endpoint += "&$orderby=receivedDateTime"
#getting the total count of messages in each round
endpoint += "&$count=true"
messages_response = helper.send_http_request(graph_url + endpoint,
"GET",
headers=headers,
parameters=None,
timeout=(15.0, 15.0)).json()
helper.log_info("Retrieving " + str(messages_response['@odata.count']) +
" messages")
messages = []
#Routine that iterates through the messages. Uses the @odata.nextLink values to find the next endpoint to query.
messages.append(messages_response['value'])
#Calculate how many pages of 980 messages we'll attempt based on the interval value. Helps to keep requests within API limits.
interval_in_seconds = int(helper.get_arg('interval'))
url_count_limit = (interval_in_seconds // 60) - 1
if url_count_limit > 0:
url_count = 0
while ("@odata.nextLink" in messages_response) and (is_https(
messages_response["@odata.nextLink"])):
if url_count < url_count_limit:
nextlinkurl = messages_response["@odata.nextLink"]
messages_response = helper.send_http_request(
nextlinkurl,
"GET",
headers=headers,
parameters=None,
timeout=(15.0, 15.0)).json()
messages.append(messages_response['value'])
url_count += 1
else:
helper.log_debug("Protecting API limits, breaking out")
break
#Routine to find attachments in messages. This caters for both standard, as well as inline attachments. MS Graph doesn't list inline attachments in the "hasAttachments" value, this fixes that.
message_data = []
attach_data = []
for message in messages:
for item in message:
message_items = {}
message_items['_time'] = item['receivedDateTime']
message_items['to'] = item['toRecipients']
message_items['from'] = item['from']
message_items['sender'] = item['sender']
message_items['subject'] = item['subject']
message_items['id'] = item['id']
message_items['internetMessageId'] = item['internetMessageId']
message_items['ccRecipients'] = item['ccRecipients']
message_items['bccRecipients'] = item['bccRecipients']
message_items['replyTo'] = item['replyTo']
message_items['hasAttachments'] = item['hasAttachments']
message_body = item['body']['content']
body_preview = item['bodyPreview']
attachments = item['attachments']
single_value_properties = item['singleValueExtendedProperties']
if 'internetMessageHeaders' in item:
internet_message_headers = item['internetMessageHeaders']
if helper.get_arg('get_internet_headers'):
message_items[
'Internet-Headers'] = internet_message_headers
#message path calculations
message_path = []
path_item = {}
for item in internet_message_headers:
if item['name'] == "Received":
path_item = item
message_path.append(path_item)
src_line = str(message_path[-1])
dest_line = str(message_path[0])
re_by = re.compile(r'(?<=\bby\s)(\S+)')
re_from = re.compile(r'(?<=\bfrom\s)(\S+)')
dest = re_by.search(dest_line)
if re_from.search(src_line):
src = re_from.search(src_line)
elif re_by.search(src_line):
src = re_by.search(src_line)
message_items['src'] = str(src[0])
message_items['dest'] = str(dest[0])
if helper.get_arg('get_message_path'):
message_items['message_path'] = message_path
if helper.get_arg('get_x_headers'):
x_headers = []
x_header_item = {}
for item in internet_message_headers:
if "X-" in item['name']:
x_header_item = item
x_headers.append(x_header_item)
message_items['X-Headers'] = x_headers
if helper.get_arg('get_auth_results'):
auth_results = []
auth_results_item = {}
for item in internet_message_headers:
if "Authentication-Results" in item['name']:
auth_results_item = item
auth_results.append(auth_results_item)
message_items['Authentication-Results'] = auth_results
if helper.get_arg('get_spf_results'):
spf_results = []
spf_results_item = {}
for item in internet_message_headers:
if "Received-SPF" in item['name']:
spf_results_item = item
spf_results.append(spf_results_item)
message_items['Received-SPF'] = spf_results
if helper.get_arg('get_dkim_signature'):
dkim_sig = []
dkim_sig_item = {}
for item in internet_message_headers:
if "DKIM-Signature" in item['name']:
dkim_sig_item = item
dkim_sig.append(dkim_sig_item)
message_items['DKIM-Signature'] = dkim_sig
#tracking pixel detection
if pixeltrack_re.search(message_body):
pixel_data = pixeltrack_re.search(message_body)
message_items['tracking_pixel'] = "true"
message_items['tracking_pixel_data'] = pixel_data.group(0)
else:
message_items['tracking_pixel'] = "false"
#size mapping
for item in single_value_properties:
if item['id'] == "Long 0xe08":
message_items['size'] = item['value']
if helper.get_arg('get_body'):
message_items['body'] = message_body
if helper.get_arg('get_body_preview'):
message_items['bodyPreview'] = body_preview
if helper.get_arg('get_internet_headers'):
message_items['Internet-Headers'] = internet_message_headers
if helper.get_arg('get_attachment_info'):
message_items['attachments'] = attachments
if helper.get_arg('get_body'):
if helper.get_arg('extract_iocs'):
iocs = extract_iocs(helper, message_items["body"])
email_iocs = []
for ioc in iocs:
if not ioc in email_iocs:
email_iocs.append(ioc)
if email_iocs:
message_items['iocs'] = email_iocs
if helper.get_arg('get_attachment_info'):
if message_items['attachments'] is not None:
for attachment in message_items["attachments"]:
#Looks for itemAttachment type, which is a contact, event, or message that's attached.
if attachment[
"@odata.type"] == "#microsoft.graph.itemAttachment":
my_added_data = {}
my_added_data['name'] = attachment['name']
my_added_data['odata_type'] = attachment[
'@odata.type']
my_added_data['id'] = attachment['id']
my_added_data['contentType'] = attachment[
'contentType']
my_added_data['size'] = attachment['size']
attach_data.append(my_added_data)
#Looks for referenceAttachment type, which is a link to a file on OneDrive or other supported storage location
if attachment[
"@odata.type"] == "#microsoft.graph.referenceAttachment":
my_added_data = {}
my_added_data['name'] = attachment['name']
my_added_data['odata_type'] = attachment[
'@odata.type']
my_added_data['id'] = attachment['id']
my_added_data['contentType'] = attachment[
'contentType']
my_added_data['size'] = attachment['size']
attach_data.append(my_added_data)
#Looks for fileAttachment type, which is a standard email attachment.
if attachment[
"@odata.type"] == "#microsoft.graph.fileAttachment":
my_added_data = {}
attach_b64decode = base64.b64decode(
attachment['contentBytes'])
#Selects which hashing algorithm (md5, sha1, sha256) to use on the attachment.
if helper.get_arg(
'get_attachment_info') and helper.get_arg(
'file_hash_algorithm') == 'md5':
hash_object = hashlib.md5(attach_b64decode)
if helper.get_arg(
'get_attachment_info') and helper.get_arg(
'file_hash_algorithm') == 'sha1':
hash_object = hashlib.sha1(attach_b64decode)
if helper.get_arg(
'get_attachment_info') and helper.get_arg(
'file_hash_algorithm') == 'sha256':
hash_object = hashlib.sha256(attach_b64decode)
att_hash = hash_object.hexdigest()
my_added_data['name'] = attachment['name']
my_added_data['odata_type'] = attachment[
'@odata.type']
my_added_data['id'] = attachment['id']
my_added_data['contentType'] = attachment[
'contentType']
my_added_data['size'] = attachment['size']
my_added_data['file_hash'] = att_hash
#Attempts to open up zip file to list file names and hashes if the option is selected in the input.
if helper.get_arg(
'get_attachment_info'
) and helper.get_arg(
'read_zip_files'
) and attachment[
'@odata.mediaContentType'] == 'application/zip':
filedata_encoded = attachment[
'contentBytes'].encode()
file_bytes = base64.b64decode(filedata_encoded)
zipbytes = io.BytesIO(file_bytes)
try:
zipfile = ZipFile(zipbytes)
zipmembers = zipfile.namelist()
zip_files = []
zip_hashes = []
for file in zipmembers:
zip_read = zipfile.read(file)
if helper.get_arg('file_hash_algorithm'
) == 'md5':
hash_object = hashlib.md5(zip_read)
if helper.get_arg('file_hash_algorithm'
) == 'sha1':
hash_object = hashlib.sha1(
zip_read)
if helper.get_arg('file_hash_algorithm'
) == 'sha256':
hash_object = hashlib.sha256(
zip_read)
zip_hash = hash_object.hexdigest()
if not file in zip_files:
zip_files.append(file)
zip_hashes.append(zip_hash)
if zip_files:
my_added_data[
'zip_files'] = zip_files
my_added_data[
'zip_hashes'] = zip_hashes
except:
my_added_data[
'attention'] = 'could not extract the zip file, may be encrypted'
#Routine to gather info on CSV file types.
if helper.get_arg(
'get_attachment_info'
) and attachment[
'@odata.mediaContentType'] == 'text/csv':
filedata_encoded = attachment[
'contentBytes'].encode()
file_bytes = base64.b64decode(filedata_encoded)
csvbytes = io.BytesIO(file_bytes)
try:
csvstring = csvbytes.read().decode('utf-8')
if helper.get_arg('extract_iocs'):
iocs = extract_iocs(helper, csvstring)
csv_iocs = []
for ioc in iocs:
if not ioc in csv_iocs:
csv_iocs.append(ioc)
if csv_iocs:
my_added_data['iocs'] = csv_iocs
#Will attempt to ingest the actual contents of the CSV file if this option is selected in the input.
if 'csv' in helper.get_arg(
'attachment_data_ingest'):
my_added_data['csv_data'] = csvstring
except:
my_added_data[
'attention'] = 'could not parse the csv document, may be encrypted'
#Routine to gather info on HTML file types.
if helper.get_arg(
'get_attachment_info'
) and attachment[
'@odata.mediaContentType'] == 'text/html':
filedata_encoded = attachment[
'contentBytes'].encode()
file_bytes = base64.b64decode(filedata_encoded)
try:
uncooked_soup = html.unescape(
str(file_bytes))
soup = BeautifulSoup(uncooked_soup)
soup_data = str(soup)
if helper.get_arg('extract_iocs'):
iocs = extract_iocs(helper, soup_data)
html_iocs = []
for ioc in iocs:
if not ioc in html_iocs:
html_iocs.append(ioc)
if html_iocs:
my_added_data['iocs'] = html_iocs
#Will attempt to ingest the actual contents of the HTML file if this option is selected in the input.
if 'html' in helper.get_arg(
'attachment_data_ingest'):
my_added_data['html_data'] = soup_data
except:
my_added_data[
'attention'] = 'could not parse the html document, may be encrypted'
#Routine to gather info on PDF file types.
if helper.get_arg(
'get_attachment_info'
) and attachment[
'@odata.mediaContentType'] == 'application/pdf':
filedata_encoded = attachment[
'contentBytes'].encode()
file_bytes = base64.b64decode(filedata_encoded)
pdf_content = io.BytesIO(file_bytes)
output_string = StringIO()
try:
parser = PDFParser(pdf_content)
doc = PDFDocument(parser)
rsrcmgr = PDFResourceManager()
device = TextConverter(rsrcmgr,
output_string,
laparams=LAParams())
interpreter = PDFPageInterpreter(
rsrcmgr, device)
for page in PDFPage.create_pages(doc):
interpreter.process_page(page)
pdf_text = output_string.getvalue()
if helper.get_arg('extract_iocs'):
iocs = extract_iocs(helper, pdf_text)
pdf_iocs = []
for ioc in iocs:
if not ioc in pdf_iocs:
pdf_iocs.append(ioc)
if pdf_iocs:
my_added_data[
'iocs'] = pdf_iocs
#Will attempt to ingest the actual contents of the PDF file if this option is selected in the input.
if 'pdf' in helper.get_arg(
'attachment_data_ingest'):
my_added_data['pdf_data'] = pdf_text
except:
my_added_data[
'attention'] = 'could not parse the pdf document, may be encrypted'
#Routine to gather info on XML file types.
if helper.get_arg(
'get_attachment_info'
) and attachment[
'@odata.mediaContentType'] == 'text/xml':
filedata_encoded = attachment[
'contentBytes'].encode()
file_bytes = base64.b64decode(filedata_encoded)
try:
soup = BeautifulSoup(file_bytes, 'lxml')
soup_data = str(soup)
if helper.get_arg('extract_iocs'):
iocs = extract_iocs(helper, soup_data)
xml_iocs = []
for ioc in iocs:
if not ioc in xml_iocs:
xml_iocs.append(ioc)
if xml_iocs:
my_added_data['iocs'] = xml_iocs
#Will attempt to ingest the actual contents of the XML file if this option is selected in the input.
if 'xml' in helper.get_arg(
'attachment_data_ingest'):
my_added_data['xml_data'] = soup_data
except:
my_added_data[
'attention'] = 'could not parse the xml document, may be encrypted'
#Routine to do macro analysis on files of supported content types listed below if selected in the input setup. This uses OLEVBA tools to detect macros in the attachment, then analyses the macros.
if helper.get_arg(
'get_attachment_info') and helper.get_arg(
'macro_analysis'):
filename = attachment['name']
#Content types supported by OLEVBA.
supported_content = [
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
'application/vnd.openxmlformats-officedocument.spreadsheetml.template',
'application/vnd.ms-excel.sheet.macroenabled.12',
'application/vnd.ms-excel.template.macroenabled.12',
'application/vnd.ms-excel.addin.macroenabled.12',
'application/vnd.ms-excel.sheet.binary.macroenabled.12',
'application/vnd.ms-excel',
'application/xml',
'application/vnd.ms-powerpoint',
'application/vnd.openxmlformats-officedocument.presentationml.presentation',
'application/vnd.openxmlformats-officedocument.presentationml.template',
'application/vnd.openxmlformats-officedocument.presentationml.slideshow',
'application/vnd.ms-powerpoint.addin.macroenabled.12',
'application/vnd.ms-powerpoint.presentation.macroenabled.12',
'application/vnd.ms-powerpoint.template.macroenabled.12',
'application/vnd.ms-powerpoint.slideshow.macroenabled.12',
'application/msword',
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'application/vnd.openxmlformats-officedocument.wordprocessingml.template',
'application/vnd.ms-word.document.macroenabled.12',
'application/vnd.ms-word.template.macroenabled.12'
]
if attachment[
'@odata.mediaContentType'] in supported_content:
filedata_encoded = attachment[
'contentBytes'].encode()
file_bytes = base64.b64decode(
filedata_encoded)
try:
vbaparser = VBA_Parser(filename,
data=file_bytes)
if vbaparser.detect_vba_macros():
my_added_data[
'macros_exist'] = "true"
macro_analysis = VBA_Parser.analyze_macros(
vbaparser)
helper.log_debug(
"GET Response: " + json.dumps(
macro_analysis, indent=4))
if macro_analysis == []:
my_added_data[
'macro_analysis'] = "Macro doesn't look bad, but I never trust macros."
else:
my_added_data[
'macros_analysis'] = macro_analysis
else:
my_added_data[
'macros_exist'] = "false"
except:
my_added_data[
'attention'] = 'could not extract the office document, may be encrypted'
attach_data.append(my_added_data)
message_items['attachments'] = attach_data
message_data.append(message_items)
_write_events(helper, ew, messages=message_data)
_purge_messages(helper, messages)