def get_report(self):
""" Return oletools report or create if not already cached. """
if self.sample.oletools_report is not None:
return self.sample.oletools_report
report = {
'autoexec': [],
'suspicious': [],
}
file_path = self.sample.file_path
try:
vbaparser = VBA_Parser(file_path)
# VBA_Parser reports macros for office documents
report['has_macros'] = vbaparser.detect_vba_macros(
) or vbaparser.detect_xlm_macros()
try:
report['vba'] = vbaparser.reveal()
except TypeError:
# office document with no macros
pass
all_macros = vbaparser.extract_all_macros()
if (report['has_macros'] and len(all_macros) == 1
and isinstance(all_macros[0], tuple)
and len(all_macros[0]) >= 3
and all_macros[0][2] == file_path):
logger.warning(
"Buggy oletools version detected, result overridden. May "
"lead to false negatives, please update to fixed version")
report['has_macros'] = False
if vbaparser.detect_vba_macros():
vb_code = vbaparser.extract_all_macros()
for (_, _, _, c) in vb_code:
autoexec = detect_autoexec(c)
if len(autoexec) >= 1:
report['autoexec'].append(autoexec[0])
suspicious = detect_suspicious(c)
if len(suspicious) >= 1:
report['suspicious'].append(suspicious[0])
vbaparser.close()
except IOError:
raise
except (TypeError, FileOpenError):
# The given file is not an office document.
pass
except Exception as error:
logger.exception(error)
report = OletoolsReport(report)
self.sample.register_oletools_report(report)
return report
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 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 parse_vba(self, save_path):
save = False
vbaparser = VBA_Parser(__sessions__.current.file.path)
# Check for Macros
if not vbaparser.detect_vba_macros():
self.log('error', "No Macro's Detected")
return
self.log('info', "Macro's Detected")
#try:
if True:
an_results = {'AutoExec':[], 'Suspicious':[], 'IOC':[], 'Hex String':[], 'Base64 String':[], 'Dridex String':[], 'VBA string':[]}
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
self.log('info', "Stream Details")
self.log('item', "OLE Stream: {0}".format(string_clean(stream_path)))
self.log('item', "VBA Filename: {0}".format(string_clean(vba_filename)))
# Analyse the VBA Code
vba_scanner = VBA_Scanner(vba_code)
analysis = vba_scanner.scan(include_decoded_strings=True)
for kw_type, keyword, description in analysis:
an_results[kw_type].append([string_clean_hex(keyword), description])
# Save the code to external File
if save_path:
try:
with open(save_path, 'a') as out:
out.write(vba_code)
save = True
except:
self.log('error', "Unable to write to {0}".format(save_path))
return
# Print all Tables together
self.log('info', "AutoRun Macros Found")
self.log('table', dict(header=['Method', 'Description'], rows=an_results['AutoExec']))
self.log('info', "Suspicious Keywords Found")
self.log('table', dict(header=['KeyWord', 'Description'], rows=an_results['Suspicious']))
self.log('info', "Possible IOC's")
self.log('table', dict(header=['IOC', 'Type'], rows=an_results['IOC']))
self.log('info', "Hex Strings")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['Hex String']))
self.log('info', "Base64 Strings")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['Base64 String']))
self.log('info', "Dridex String")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['Dridex String']))
self.log('info', "VBA string")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['VBA string']))
if save:
self.log('success', "Writing VBA Code to {0}".format(save_path))
#except:
#self.log('error', "Unable to Process File")
# Close the file
vbaparser.close()
def EXTRACT_VBA_MACRO(s, buff):
EXTRACT_MACRO = {}
counter = 0
### TODO: REMOVE THIS WORKAROUND ONCE MODULE AUTHOR FIXES CODE ###
### Reference: http://stackoverflow.com/questions/32261679/strange-issue-using-logging-module-in-python/32264445#32264445
### Reference: https://bitbucket.org/decalage/oletools/issues/26/use-of-logger
### /dev/null used instead of NullHandler for 2.6 compatibility
logging.getLogger('workaround').root.addHandler(
logging.FileHandler('/dev/null'))
###
vba = VBA_Parser('None', data=buff)
if not vba.detect_vba_macros():
return EXTRACT_MACRO
for (filename, stream_path, vba_filename,
vba_code) in vba.extract_macros():
CHILD_MACRO = OrderedDict([('OLE Stream', stream_path),
('VBA Filename',
vba_filename.decode('ascii', 'ignore')),
('Scan', scan_macro(vba_code)),
('Buffer', vba_code)])
EXTRACT_MACRO['Object_%s' % counter] = CHILD_MACRO
counter += 1
return EXTRACT_MACRO
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 EXTRACT_VBA_MACRO(s, buff):
EXTRACT_MACRO = {}
counter = 0
### TODO: REMOVE THIS WORKAROUND ONCE MODULE AUTHOR FIXES CODE ###
### Reference: http://stackoverflow.com/questions/32261679/strange-issue-using-logging-module-in-python/32264445#32264445
### Reference: https://bitbucket.org/decalage/oletools/issues/26/use-of-logger
### /dev/null used instead of NullHandler for 2.6 compatibility
logging.getLogger('workaround').root.addHandler(logging.FileHandler('/dev/null'))
###
vba = VBA_Parser('None', data=buff)
if not vba.detect_vba_macros():
return EXTRACT_MACRO
for (filename, stream_path, vba_filename, vba_code) in vba.extract_macros():
CHILD_MACRO = OrderedDict([('OLE Stream', stream_path),
('VBA Filename', vba_filename.decode('ascii', 'ignore')),
('Scan', scan_macro(vba_code)),
('Buffer', vba_code)])
EXTRACT_MACRO['Object_%s' % counter] = CHILD_MACRO
counter += 1
return EXTRACT_MACRO
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 extract_macros_from_office2003(fullpath, fileobj=None):
'''
:return: [(host_fullpath, filename_from_host, data), ... ]
'''
from oletools.olevba import VBA_Parser
vp = VBA_Parser(fullpath, data=fileobj.read() if fileobj else None)
r = []
try:
if vp.detect_vba_macros():
macros = vp.extract_all_macros()
assert (macros
) # macros detect, if cannot extact, must be error occured
if macros:
for (subfullpath, stream_path, vba_filename,
vba_code) in macros:
a = os.path.basename(fullpath)
b = os.path.basename(subfullpath)
vba_filename += u'.vba'
sub = (io_text_arg(fullpath),
io_text_arg(vba_filename if a == b else u'{0}_{1}'.
format(b, vba_filename)), vba_code)
r.append(sub)
except:
pass
finally:
vp.close()
return r
def parse_vba(self, save_path):
save = False
vbaparser = VBA_Parser(__sessions__.current.file.path)
# Check for Macros
if not vbaparser.detect_vba_macros():
self.log('error', "No Macro's Detected")
return
self.log('info', "Macro's Detected")
#try:
if True:
an_results = {'AutoExec':[], 'Suspicious':[], 'IOC':[], 'Hex String':[], 'Base64 String':[], 'Dridex String':[], 'VBA string':[]}
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
self.log('info', "Stream Details")
self.log('item', "OLE Stream: {0}".format(string_clean(stream_path)))
self.log('item', "VBA Filename: {0}".format(string_clean(vba_filename)))
# Analyse the VBA Code
vba_scanner = VBA_Scanner(vba_code)
analysis = vba_scanner.scan(include_decoded_strings=True)
for kw_type, keyword, description in analysis:
an_results[kw_type].append([string_clean_hex(keyword), description])
# Save the code to external File
if save_path:
try:
with open(save_path, 'a') as out:
out.write(vba_code)
save = True
except:
self.log('error', "Unable to write to {0}".format(save_path))
return
# Print all Tables together
self.log('info', "AutoRun Macros Found")
self.log('table', dict(header=['Method', 'Description'], rows=an_results['AutoExec']))
self.log('info', "Suspicious Keywords Found")
self.log('table', dict(header=['KeyWord', 'Description'], rows=an_results['Suspicious']))
self.log('info', "Possible IOC's")
self.log('table', dict(header=['IOC', 'Type'], rows=an_results['IOC']))
self.log('info', "Hex Strings")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['Hex String']))
self.log('info', "Base64 Strings")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['Base64 String']))
self.log('info', "Dridex String")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['Dridex String']))
self.log('info', "VBA string")
self.log('table', dict(header=['Decoded', 'Raw'], rows=an_results['VBA string']))
if save:
self.log('success', "Writing VBA Code to {0}".format(save_path))
#except:
#self.log('error', "Unable to Process File")
# Close the file
vbaparser.close()
def get_report(self, sample):
""" Return oletools report or create if not already cached. """
if sample.oletools_report != None:
return sample.oletools_report
report = {}
try:
vbaparser = VBA_Parser(sample.file_path)
# VBA_Parser reports macros for office documents
report['has_macros'] = vbaparser.detect_vba_macros(
) or vbaparser.detect_xlm_macros()
try:
report['vba'] = vbaparser.reveal()
except TypeError:
# no macros
pass
vbaparser.close()
except IOError:
raise
except (TypeError, FileOpenError):
# The given file is not an office document.
pass
except Exception as error:
logger.exception(error)
sample.register_oletools_report(OletoolsReport(report))
return report
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 process_file_scanexpr (container, filename, data):
"""
Process a single file
:param container: str, path and filename of container if the file is within
a zip archive, None otherwise.
:param filename: str, path and filename of file on disk, or within the container.
:param data: bytes, content of the file if it is in a container, None if it is a file on disk.
"""
#TODO: replace print by writing to a provided output file (sys.stdout by default)
if container:
display_filename = '%s in %s' % (filename, container)
else:
display_filename = filename
print '='*79
print 'FILE:', display_filename
all_code = ''
try:
#TODO: handle olefile errors, when an OLE file is malformed
vba = VBA_Parser(filename, data)
print 'Type:', vba.type
if vba.detect_vba_macros():
#print 'Contains VBA Macros:'
for (subfilename, stream_path, vba_filename, vba_code) in vba.extract_macros():
# hide attribute lines:
#TODO: option to disable attribute filtering
vba_code_filtered = filter_vba(vba_code)
print '-'*79
print 'VBA MACRO %s ' % vba_filename
print 'in file: %s - OLE stream: %s' % (subfilename, repr(stream_path))
print '- '*39
# detect empty macros:
if vba_code_filtered.strip() == '':
print '(empty macro)'
else:
# TODO: option to display code
print vba_code_filtered
vba_code = vba_collapse_long_lines(vba_code)
all_code += '\n' + vba_code
print '-'*79
print 'EVALUATED VBA EXPRESSIONS:'
t = prettytable.PrettyTable(('Obfuscated expression', 'Evaluated value'))
t.align = 'l'
t.max_width['Obfuscated expression'] = 36
t.max_width['Evaluated value'] = 36
for expression, expr_eval in scan_expressions(all_code):
t.add_row((repr(expression), repr(expr_eval)))
print t
else:
print 'No VBA macros found.'
except: #TypeError:
#raise
#TODO: print more info if debug mode
#print sys.exc_value
# display the exception with full stack trace for debugging, but do not stop:
traceback.print_exc()
print ''
def is_file_has_VBA_macros(self):
"""Check if file has VBA macros."""
file_path = self.file_path
vbaparser = VBA_Parser(file_path)
print('The file type is "%s"' % (vbaparser.type))
report = vbaparser.detect_vba_macros()
vbaparser.close()
return report
def parse_vba(self, save_path):
vba = VBA_Parser(__sessions__.current.file.path)
# Check for Macros
if not vba.detect_vba_macros():
self.log('error', "No Macro's Detected")
return
self.log('info', "Macro's Detected")
try:
for (filename, stream_path, vba_filename,
vba_code) in vba.extract_macros():
self.log('info', "Stream Details")
self.log('item', "OLE Stream: {0}".format(stream_path))
self.log('item', "VBA Filename: {0}".format(vba_filename))
autoexec_keywords = detect_autoexec(vba_code)
if autoexec_keywords:
self.log('info', "AutoRun Macros Found")
rows = []
for keyword, description in autoexec_keywords:
rows.append([keyword, description])
self.log(
'table',
dict(header=['KeyWord', 'Description'], rows=rows))
# Match Keyword Types
suspicious_keywords = detect_suspicious(vba_code)
if suspicious_keywords:
self.log('info', "Suspicious Keywords Found")
rows = []
for keyword, description in suspicious_keywords:
rows.append([keyword, description])
self.log(
'table',
dict(header=['KeyWord', 'Description'], rows=rows))
# Match IOCs
patterns = detect_patterns(vba_code)
if patterns:
self.log('info', "Suspicious Keywords Found")
rows = []
for pattern_type, value in patterns:
rows.append([pattern_type, value])
self.log('table',
dict(header=['Pattern', 'Value'], rows=rows))
# Save the code to external File
if save_path:
try:
with open(save_path, 'w') as out:
out.write(vba_code)
self.log('info',
"Writing VBA Code to {0}".format(save_path))
except:
self.log('Error',
"Unable to write to {0}".format(save_path))
return
except:
self.log('Error', "Unable to Process File")
# Close the file
vba.close()
def getVBA(self, myfile, source='filepath'):
'''
Given a file, parses out the stream paths, vba code, and vba filenames for each.
:param myfile: filename
:param source: type of data being passed in. Either "filepath" to indicate we need to read from disk or
"filecontents" meaning that the file contents are being passed as a parameter.
:return: pandas Series that can be used in concert with the pandas DataFrame apply method
'''
if source == 'filepath':
filedata = open(myfile, 'rb').read()
else:
filedata = myfile
entry = {}
try:
vbaparser = VBA_Parser('mmbot', data=filedata)
allcode = ''
pathnames = ''
filenames = ''
if vbaparser.detect_vba_macros():
filenameslist = []
pathnameslist = []
vbacodelist = []
for (filename, stream_path, filename_vba,
extracted_vba) in vbaparser.extract_macros():
vbacodelist.append(extracted_vba.decode("ascii", "ignore"))
#vbacodelist.append(extracted_vba.decode('utf8', 'ignore'))
if pathnames is None:
pathnameslist.append(
stream_path.decode("ascii", "ignore"))
filenameslist.append(
filename_vba.decode("ascii", "ignore"))
else:
pathnameslist.append(
stream_path.decode("ascii", "ignore"))
filenameslist.append(
filename_vba.decode("ascii", "ignore"))
allcode = "\n\n\n\n".join(vbacodelist)
filenames = ", ".join(filenameslist)
pathnames = ", ".join(pathnameslist)
else:
pathnames = 'No VBA Macros found'
filenames = 'No VBA Macros found'
allcode = 'No VBA Macros found'
except Exception as e:
pathnames = 'Error:' + str(e)
filenames = 'Error:' + str(e)
allcode = 'Error:' + str(e)
return pd.Series({
'extracted_vba': allcode,
'stream_path': pathnames,
'filename_vba': filenames
})
def parse_vba(self, save_path):
save = False
vba = VBA_Parser(__sessions__.current.file.path)
# Check for Macros
if not vba.detect_vba_macros():
self.log('error', "No Macro's Detected")
return
self.log('info', "Macro's Detected")
try:
run_rows = []
word_rows = []
pattern_rows = []
for (filename, stream_path, vba_filename, vba_code) in vba.extract_macros():
self.log('info', "Stream Details")
self.log('item', "OLE Stream: {0}".format(string_clean(stream_path)))
self.log('item', "VBA Filename: {0}".format(string_clean(vba_filename)))
autoexec_keywords = detect_autoexec(vba_code)
if autoexec_keywords:
for keyword, description in autoexec_keywords:
run_rows.append([keyword, description])
# Match Keyword Types
suspicious_keywords = detect_suspicious(vba_code)
if suspicious_keywords:
for keyword, description in suspicious_keywords:
word_rows.append([keyword, description])
# Match IOCs
patterns = detect_patterns(vba_code)
if patterns:
for pattern_type, value in patterns:
pattern_rows.append([pattern_type, value])
# Save the code to external File
if save_path:
try:
with open(save_path, 'a') as out:
out.write(vba_code)
save = True
except:
self.log('Error', "Unable to write to {0}".format(save_path))
return
# Print all Tables together
self.log('info', "AutoRun Macros Found")
self.log('table', dict(header=['KeyWord', 'Description'], rows=run_rows))
self.log('info', "Suspicious Keywords Found")
self.log('table', dict(header=['KeyWord', 'Description'], rows=word_rows))
self.log('info', "Suspicious Patterns Found")
self.log('table', dict(header=['Pattern', 'Value'], rows=pattern_rows))
if save:
self.log('success', "Writing VBA Code to {0}".format(save_path))
except:
self.log('Error', "Unable to Process File")
# Close the file
vba.close()
def POE(logdir, targetfile, logging, debug):
if (logging == True):
LOG = logger()
newlogentry = ''
macro_dump_data = ''
FI = fileio()
try:
filedata = open(targetfile.filename, 'rb').read()
vbaparser = VBA_Parser(targetfile.filename, data=filedata)
if vbaparser.detect_vba_macros():
print '[*] VBA macros found - Extracting...\n'
if (logging == True):
newlogentry = 'VBA macros found - Extracting...'
LOG.WriteLog(logdir, targetfile.filename, newlogentry)
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
macro_dump_data += '-' * 79 + '\n'
try:
macro_dump_data += 'Filename :' + filename.encode("ascii", "replace") + '\n'
macro_dump_data += 'OLE stream :' + stream_path.encode("ascii", "replace") + '\n'
macro_dump_data += 'VBA filename:' + vba_filename.encode("ascii", "replace") + '\n'
except Exception, e:
print '[x] Current macro - unable to print Filename, OLE stream or VBA filename due to encoding issue (Unicode?): ', e
macro_dump_data += '-' * 79 + '\n'
macro_dump_data += vba_code
FI.WriteLogFile(logdir + vba_filename, macro_dump_data)
try:
print '[*] Macro ' + vba_filename.encode("ascii", "replace") + ' extracted to: ' + logdir + vba_filename.encode("ascii", "replace")
targetfile.macros.append(logdir + vba_filename.encode("ascii", "replace"))
if (logging == True):
newlogentry = 'Macro ' + vba_filename.encode("ascii", "replace") + ' extracted to: <a href=\"' + logdir + vba_filename.encode("ascii", "replace") + '\">' + vba_filename.encode("ascii", "replace") + '</a>'
LOG.WriteLog(logdir, targetfile.filename, newlogentry)
if (debug == True):
print '-'*79
print 'Filename :', filename.encode("ascii", "replace")
print 'OLE stream :', stream_path.encode("ascii", "replace")
print 'VBA filename:', vba_filename.encode("utf-8", "ignore")
print '-'*79
except Exception, e:
print '[x] Current macro - unable print Filename, OLE stream or VBA filename due to encoding issue: (Unicode?)', e
if (debug == True):
print vba_code
macro_dump_data = ''
print 'Macro List'
for mlist in targetfile.macros:
print mlist
def get_macro(self):
"""
Get Macros from an Office file and write them to a text file
"""
try:
self.mk_tmp_dir()
print "Getting Macros from {}".format(self.file)
vb = VBA_Parser(self.file, relaxed=True)
if vb.detect_vba_macros():
with open("{}{}macros.txt".format(self.tmp_dir, os.sep), "w") as macro_file:
for (subfilename, stream_path, vba_filename, vba_code) in vb.extract_all_macros():
macro_file.write(vba_code)
except Exception as e:
print "get_macro Exception: {}".format(e)
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 get_vba_code(self):
"""Code analysis for malicious parts. Returns malicious code, if any."""
if not self.has_macros:
return "Документ не содержит макросов!"
vbaparser = VBA_Parser(self.file_path)
vbaparser.detect_vba_macros()
code_list = list()
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
code_list.append(vba_code)
code = vba_code
report_vba = code_list[0]
macros_infos = self.macros_infos
for i in range(len(macros_infos)):
if macros_infos[i]['number'] > 0:
macro_code = macros_infos[i]['function'](code)
for i in macro_code:
for j in i:
report_vba += j
vbaparser.close()
return report_vba
def get_vba_source_from_excel(filename):
vbaparser = VBA_Parser(filename)
if vbaparser.detect_vba_macros():
print('VBA Macros found')
else:
print('No VBA Macros found')
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
print('-' * 79)
print('Filename :', filename)
print('OLE stream :', stream_path)
print('VBA filename:', vba_filename)
print('- ' * 39)
print(vba_code)
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 has_office_macros(office_file):
"""
Detects macros in Microsoft Office documents.
:param office_file: The MS Office document to check for macros.
:return: True if macros where found, otherwise False.
If VBA_Parser crashes it returns False too.
"""
file_extension = office_file.split('.')[-1]
if file_extension not in ms_office_extensions:
return False
try:
# VBA_Parser reports macros for office documents
vbaparser = VBA_Parser(office_file)
return vbaparser.detect_vba_macros()
except TypeError:
# The given file is not an office document.
return False
except Exception as e:
logger.exception(e)
return False
def get_office_file_startup_command(extension, file_path):
start_command = ["cmd.exe", "/C", "start"]
if is_office_word_file(extension):
start_command.append("winword.exe")
elif is_office_excel_file(extension):
start_command.append("excel.exe")
elif is_office_powerpoint_file(extension):
start_command.append("powerpnt.exe")
else:
log.warning(f"Unknown office file extension {extension}.")
return None
start_command.extend(["/t", "%f"])
vbaparser = VBA_Parser(file_path)
if vbaparser.detect_vba_macros():
outer_macros = get_outer_nodes_from_vba_file(file_path)
if not outer_macros:
outer_macros = []
for outer_macro in outer_macros:
start_command.append(f"/m{outer_macro}")
return subprocess.list2cmdline(start_command)
def get_report(self, sample):
""" Return oletools report or create if not already cached. """
if sample.oletools_report != None:
return sample.oletools_report
report = {}
if sample.file_extension not in self.MS_OFFICE_EXTENSIONS:
raise OleNotAnOfficeDocumentException(sample.file_extension)
try:
vbaparser = VBA_Parser(sample.file_path)
# List from oletools/olevba.py#L553
oletype = ('OLE', 'OpenXML', 'FlatOPC_XML', 'Word2003_XML',
'MHTML', 'PPT')
# check if ole detects it as an office file
if vbaparser.type not in oletype:
raise OleNotAnOfficeDocumentException(sample.file_extension)
# VBA_Parser reports macros for office documents
report['has_macros'] = vbaparser.detect_vba_macros(
) or vbaparser.detect_xlm_macros()
try:
report['vba'] = vbaparser.reveal()
except TypeError:
# no macros
pass
vbaparser.close()
except IOError:
raise
except TypeError:
# The given file is not an office document.
pass
except Exception as error:
logger.exception(error)
sample.register_oletools_report(OletoolsReport(report))
return report
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 check_for_macros(self, filename, file_contents, request_hash):
# noinspection PyBroadException
try:
vba_parser = VBA_Parser(filename=filename, data=file_contents)
try:
if vba_parser.detect_vba_macros():
self.ole_result.add_tag(TAG_TYPE.TECHNIQUE_MACROS,
"Contains VBA Macro(s)",
weight=TAG_WEIGHT.LOW,
usage=TAG_USAGE.IDENTIFICATION)
try:
for (subfilename, stream_path, vba_filename, vba_code) in vba_parser.extract_macros():
if vba_code.strip() == '':
continue
vba_code_sha256 = hashlib.sha256(vba_code).hexdigest()
if vba_code_sha256 == request_hash:
continue
self.all_vba.append(vba_code)
macro_section = self.macro_section_builder(vba_code)
toplevel_score = self.calculate_nested_scores(macro_section)
self.all_macros.append(Macro(vba_code, vba_code_sha256, macro_section, toplevel_score))
except Exception as e:
self.log.debug("OleVBA VBA_Parser.extract_macros failed: {}".format(str(e)))
section = ResultSection(SCORE.NULL, "OleVBA : Error extracting macros")
self.ole_result.add_section(section)
except Exception as e:
self.log.debug("OleVBA VBA_Parser.detect_vba_macros failed: {}".format(e))
section = ResultSection(SCORE.NULL, "OleVBA : Error parsing macros: {}".format(e))
self.ole_result.add_section(section)
except:
self.log.debug("OleVBA VBA_Parser constructor failed, may not be a supported OLE document")
def process_file_scanexpr (container, filename, data):
"""Process a single file.
@param container (str) Path and filename of container if the file is within
a zip archive, None otherwise.
@param filename (str) path and filename of file on disk, or within
the container.
@param data (bytes) Content of the file if it is in a container,
None if it is a file on disk.
"""
#TODO: replace print by writing to a provided output file (sys.stdout by default)
if container:
display_filename = '%s in %s' % (filename, container)
else:
display_filename = filename
safe_print('='*79)
safe_print('FILE: ' + safe_str_convert(display_filename))
all_code = ''
try:
#TODO: handle olefile errors, when an OLE file is malformed
import oletools
oletools.olevba.enable_logging()
if (log.getEffectiveLevel() == logging.DEBUG):
log.debug('opening %r' % filename)
vba = VBA_Parser(filename, data, relaxed=True)
if vba.detect_vba_macros():
# Read in document metadata.
vm = core.ViperMonkey(filename, data)
ole = olefile.OleFileIO(filename)
try:
vm.set_metadata(ole.get_metadata())
except Exception as e:
log.warning("Reading in metadata failed. Trying fallback. " + safe_str_convert(e))
vm.set_metadata(get_metadata_exif(filename))
#print 'Contains VBA Macros:'
for (subfilename, stream_path, vba_filename, vba_code) in vba.extract_macros():
# hide attribute lines:
#TODO: option to disable attribute filtering
vba_code = filter_vba(vba_code)
safe_print('-'*79)
safe_print('VBA MACRO %s ' % vba_filename)
safe_print('in file: %s - OLE stream: %s' % (subfilename, repr(stream_path)))
safe_print('- '*39)
# detect empty macros:
if vba_code.strip() == '':
safe_print('(empty macro)')
else:
# TODO: option to display code
safe_print(vba_code)
vba_code = core.vba_collapse_long_lines(vba_code)
all_code += '\n' + vba_code
safe_print('-'*79)
safe_print('EVALUATED VBA EXPRESSIONS:')
t = prettytable.PrettyTable(('Obfuscated expression', 'Evaluated value'))
t.align = 'l'
t.max_width['Obfuscated expression'] = 36
t.max_width['Evaluated value'] = 36
for expression, expr_eval in core.scan_expressions(all_code):
t.add_row((repr(expression), repr(expr_eval)))
safe_print(t)
else:
safe_print('No VBA macros found.')
except Exception as e:
log.error("Caught exception. " + safe_str_convert(e))
if (log.getEffectiveLevel() == logging.DEBUG):
traceback.print_exc()
safe_print('')
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
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)
import sys
import os
from oletools.olevba import VBA_Parser, TYPE_OLE, TYPE_OpenXML, TYPE_Word2003_XML, TYPE_MHTML, detect_autoexec, VBA_Scanner
#PYTHON 2,3버전 모두 호환
if sys.version_info[0]<= 2:
#python 2
from oletools.olevba import VBA_Parser
else:
#python 3
from oletools.olevba3 import VBA_Parser
# VBA 퍼져 온
vbaparser = VBA_Parser(sys.argv[1])
# 매크로 검사
if not vbaparser.detect_vba_macros():
print ('error', "macro not detected ")
#경고모듈 넣는 위치
sys.exit(1)
print ('info', "macro detected ! ")
for (filename, stream_path, vba_filename, vba_code) in vbaparser.extract_macros():
print ("- "*79)
print ("filename :", filename)
print ("OLE stream :", stream_path)
print ("VBA filename:", vba_filename)
print ("- "*39)
print ("vba_code",vba_code)
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
def parse_vba(self, save_path):
"""
Parse VBA scripts.
"""
save = False
vbaparser = VBA_Parser(__sessions__.current.file.path)
# Check for Macros
if not vbaparser.detect_vba_macros():
self.log("error", "No macros detected")
return
self.log("info", "Macros detected")
# try:
if True:
an_results = {
"AutoExec": [],
"Suspicious": [],
"IOC": [],
"Hex String": [],
"Base64 String": [],
"Dridex string": [],
"VBA string": []
}
for (filename, stream_path, vba_filename,
vba_code) in vbaparser.extract_macros():
self.log("info", "Stream Details")
self.log("item",
"OLE Stream: {0}".format(string_clean(stream_path)))
self.log(
"item",
"VBA Filename: {0}".format(string_clean(vba_filename)))
# Analyse the VBA Code
vba_scanner = VBA_Scanner(vba_code)
analysis = vba_scanner.scan(include_decoded_strings=True)
for kw_type, keyword, description in analysis:
an_results[kw_type].append(
[string_clean_hex(keyword), description])
# Save the code to external File
if save_path:
try:
with open(save_path, "a") as out:
out.write(vba_code)
save = True
except Exception as e:
self.log(
"error",
"Unable to write to {0}: {1}".format(save_path, e))
return
# Print all tables together
if an_results["AutoExec"]:
self.log("info", "Autorun macros found")
self.log(
"table",
dict(header=["Method", "Description"],
rows=an_results["AutoExec"]))
if an_results["Suspicious"]:
self.log("info", "Suspicious keywords found")
self.log(
"table",
dict(header=["Keyword", "Description"],
rows=an_results["Suspicious"]))
if an_results["IOC"]:
self.log("info", "Possible IOCs")
self.log("table",
dict(header=["IOC", "Type"], rows=an_results["IOC"]))
if an_results["Hex String"]:
self.log("info", "Hex strings")
self.log(
"table",
dict(header=["Decoded", "Raw"],
rows=an_results["Hex String"]))
if an_results["Base64 String"]:
self.log("info", "Base64 strings")
self.log(
"table",
dict(header=["Decoded", "Raw"],
rows=an_results["Base64 String"]))
if an_results["Dridex string"]:
self.log("info", "Dridex strings")
self.log(
"table",
dict(header=["Decoded", "Raw"],
rows=an_results["Dridex string"]))
if an_results["VBA string"]:
self.log("info", "VBA strings")
self.log(
"table",
dict(header=["Decoded", "Raw"],
rows=an_results["VBA string"]))
if save:
self.log("success",
"Writing VBA Code to {0}".format(save_path))
# Close the file
vbaparser.close()
def process_file(container,
filename,
data,
altparser=False,
strip_useless=False,
entry_points=None):
"""
Process a single file
:param container: str, path and filename of container if the file is within
a zip archive, None otherwise.
:param filename: str, path and filename of file on disk, or within the container.
:param data: bytes, content of the file if it is in a container, None if it is a file on disk.
:return A list of actions if actions found, an empty list if no actions found, and None if there
was an error.
"""
#TODO: replace print by writing to a provided output file (sys.stdout by default)
if container:
display_filename = '%s in %s' % (filename, container)
else:
display_filename = filename
print '=' * 79
print 'FILE:', display_filename
vm = ViperMonkey()
if (entry_points is not None):
for entry_point in entry_points:
vm.entry_points.append(entry_point)
try:
#TODO: handle olefile errors, when an OLE file is malformed
vba = VBA_Parser(filename, data, relaxed=True)
print 'Type:', vba.type
if vba.detect_vba_macros():
# Read in document metadata.
try:
ole = olefile.OleFileIO(filename)
vba_library.meta = ole.get_metadata()
vba_object.meta = vba_library.meta
except:
log.error("Reading in metadata failed.")
vba_library.meta = {}
# Set the output directory in which to put dumped files generated by
# the macros.
out_dir = filename + "_artifacts"
if ("/" in out_dir):
start = out_dir.rindex("/") + 1
out_dir = out_dir[start:]
out_dir = out_dir.replace(".", "").strip()
out_dir = "./" + out_dir + "/"
vba_library.out_dir = out_dir
# Parse the VBA streams.
comp_modules = parse_streams(vba, strip_useless)
if (comp_modules is None):
return None
for m in comp_modules:
if (m != "empty"):
vm.add_compiled_module(m)
# Pull out form variables.
try:
for (subfilename, stream_path,
form_variables) in vba.extract_form_strings_extended():
if form_variables is not None:
var_name = form_variables['name']
macro_name = stream_path
if ("/" in macro_name):
start = macro_name.rindex("/") + 1
macro_name = macro_name[start:]
global_var_name = (macro_name + "." + var_name).encode(
'ascii', 'ignore')
val = form_variables['value']
if (val is None):
val = ''
name = global_var_name.lower()
vm.globals[name] = val
log.debug(
"Added VBA form variable %r = %r to globals." %
(global_var_name, val))
vm.globals[name + ".tag"] = val
log.debug(
"Added VBA form variable %r = %r to globals." %
(global_var_name + ".Tag", val))
vm.globals[name + ".text"] = val
log.debug(
"Added VBA form variable %r = %r to globals." %
(global_var_name + ".Text", val))
except Exception as e:
log.error("Cannot read form strings. " + str(e))
print '-' * 79
print 'TRACING VBA CODE (entrypoint = Auto*):'
if (entry_points is not None):
log.info("Starting emulation from function(s) " +
str(entry_points))
vm.trace()
# print table of all recorded actions
print('Recorded Actions:')
print(vm.dump_actions())
print ''
return vm.actions
else:
print 'No VBA macros found.'
print ''
return []
except Exception as e:
if ("SystemExit" not in str(e)):
traceback.print_exc()
return None
def process_file (container, filename, data,
altparser=False, strip_useless=False):
"""
Process a single file
:param container: str, path and filename of container if the file is within
a zip archive, None otherwise.
:param filename: str, path and filename of file on disk, or within the container.
:param data: bytes, content of the file if it is in a container, None if it is a file on disk.
"""
#TODO: replace print by writing to a provided output file (sys.stdout by default)
if container:
display_filename = '%s in %s' % (filename, container)
else:
display_filename = filename
print '='*79
print 'FILE:', display_filename
vm = ViperMonkey()
try:
#TODO: handle olefile errors, when an OLE file is malformed
vba = VBA_Parser(filename, data, relaxed=True)
print 'Type:', vba.type
if vba.detect_vba_macros():
# Read in document metadata.
try:
ole = olefile.OleFileIO(filename)
vba_library.meta = ole.get_metadata()
except:
vba_library.meta = {}
# Parse the VBA streams.
comp_modules = parse_streams(vba, strip_useless)
for m in comp_modules:
vm.add_compiled_module(m)
# Pull out form variables.
for (subfilename, stream_path, form_variables) in vba.extract_form_strings_extended():
if form_variables is not None:
var_name = form_variables['name']
macro_name = stream_path
if ("/" in macro_name):
start = macro_name.rindex("/") + 1
macro_name = macro_name[start:]
global_var_name = (macro_name + "." + var_name).encode('ascii', 'ignore')
val = form_variables['value']
vm.globals[global_var_name.lower()] = val
log.debug("Added VBA form variable %r = %r to globals." % (global_var_name, val))
print '-'*79
print 'TRACING VBA CODE (entrypoint = Auto*):'
vm.trace()
# print table of all recorded actions
print('Recorded Actions:')
print(vm.dump_actions())
else:
print 'No VBA macros found.'
except: #TypeError:
#raise
#TODO: print more info if debug mode
#print sys.exc_value
# display the exception with full stack trace for debugging, but do not stop:
traceback.print_exc()
print ''
return res
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Analyze docx document (pretty limited for now)')
parser.add_argument('FILE', help='Docx document')
args = parser.parse_args()
if not os.path.isfile(args.FILE):
print("Invalid file path")
sys.exit(1)
# Check if any macro and extract it
vbaparser = VBA_Parser(args.FILE)
if vbaparser.detect_vba_macros():
print('VBA Macros found')
mac_name = os.path.splitext(args.FILE)[0] + '.macro'
with open(mac_name, 'w+') as f:
for (filename, stream_path, vba_filename,
vba_code) in vbaparser.extract_macros():
f.write(vba_code)
f.write('\n')
print("Macro dumped in {}".format(mac_name))
else:
print('No VBA Macros found')
# Show metadata
input_zip = ZipFile(args.FILE)
print("")
print("Metadata:")