def datalake():
url = 'https://datalake.cert.orangecyberdefense.com/api/v2/auth/token/'
auth_response = {
"access_token": "12345",
"refresh_token": "123456"
}
responses.add(responses.POST, url, json=auth_response, status=200)
return Datalake(username='******', password='******')
def main(override_args=None):
"""Method to start the script"""
# Load initial args
parser = BaseScripts.start(
'Add tags and/or comments to a specified list of hashkeys.')
parser.add_argument(
'hashkeys',
help='hashkeys of the threat to add tags and/or the comment',
nargs='*',
)
parser.add_argument(
'-i',
'--input_file',
help='hashkey txt file, with one hashkey by line',
)
parser.add_argument(
'-p',
'--public',
help='set the visibility to public',
action='store_true',
)
parser.add_argument(
'--tags',
nargs='+',
help='add a list of tags',
required=True,
)
if override_args:
args = parser.parse_args(override_args)
else:
args = parser.parse_args()
if not args.hashkeys and not args.input_file:
parser.error("either a hashkey or an input_file is required")
hashkeys = set(args.hashkeys) if args.hashkeys else set()
if args.input_file:
retrieve_hashkeys_from_file(args.input_file, hashkeys)
dtl = Datalake(env=args.env, log_level=args.loglevel)
response_dict = post_tags(hashkeys, args.tags, args.public, dtl)
if args.output:
save_output(args.output, response_dict)
logger.debug(f'Results saved in {args.output}\n')
logger.debug(f'END: add_tags.py')
def test_invalid_credentials(caplog):
url = 'https://datalake.cert.orangecyberdefense.com/api/v2/auth/token/'
api_error_msg = "Wrong credentials provided"
api_response = {'messages': api_error_msg}
responses.add(responses.POST, url, json=api_response, status=401)
with caplog.at_level(logging.ERROR):
with pytest.raises(ValueError) as ve:
Datalake(username='******', password='******')
assert str(
ve.value) == f'Could not login: {{"messages": "{api_error_msg}"}}'
assert caplog.messages == [
f'An error occurred while retrieving an access token, for URL: {url}\n'
f'response of the API: {{"messages": "{api_error_msg}"}}'
]
def main(override_args=None):
logger.debug(f'START: get_query_hash.py')
# Load initial args
parser = BaseScripts.start(
'Retrieve a query hash from a query body (a json used for the Advanced Search).'
)
required_named = parser.add_argument_group('required arguments')
required_named.add_argument(
'query_body_path',
help='path to the json file containing the query body',
)
if override_args:
args = parser.parse_args(override_args)
else:
args = parser.parse_args()
# Load api_endpoints and tokens
with open(args.query_body_path, 'r') as query_body_file:
query_body = json.load(query_body_file)
logger.debug(f'Retrieving query hash for query body: {query_body}')
dtl = Datalake(env=args.env, log_level=args.loglevel)
resp = dtl.AdvancedSearch.advanced_search_from_query_body(
query_body, limit=0, offset=0, output=Output.JSON)
if not resp or 'query_hash' not in resp:
logger.error(
"Couldn't retrieve a query hash, is the query body valid ?")
exit(1)
query_hash = resp['query_hash']
if args.output:
with open(args.output, 'w') as output:
output.write(query_hash)
logger.info(f'Query hash saved in {args.output}')
else:
logger.info(f'Query hash associated: {query_hash}')
def main(override_args=None):
"""Method to start the script"""
# Load initial args
parser = BaseScripts.start('Submit a new threat to Datalake from a file')
required_named = parser.add_argument_group('required arguments')
csv_controle = parser.add_argument_group('CSV control arguments')
required_named.add_argument(
'-i',
'--input',
help='read threats to add from FILE',
required=True,
)
required_named.add_argument(
'-a',
'--atom_type',
help='set it to define the atom type',
required=True,
)
csv_controle.add_argument(
'--is_csv',
help='set if the file input is a CSV',
action='store_true',
)
csv_controle.add_argument(
'-d',
'--delimiter',
help='set the delimiter of the CSV file',
default=',',
)
csv_controle.add_argument(
'-c',
'--column',
help='select column of the CSV file, starting at 1',
type=int,
default=1,
)
parser.add_argument(
'-p',
'--public',
help='set the visibility to public',
action='store_true',
)
parser.add_argument(
'-w',
'--whitelist',
help='set it to define the added threats as whitelist',
action='store_true',
)
parser.add_argument(
'-t',
'--threat_types',
nargs='+',
help=
'choose specific threat types and their score, like: ddos 50 scam 15',
default=[],
action='append',
)
parser.add_argument(
'--tag',
nargs='+',
help='add a list of tags',
default=[],
)
parser.add_argument(
'--link',
help='add link as external_analysis_link',
nargs='+',
)
parser.add_argument(
'--permanent',
help=
'sets override_type to permanent. Scores won\'t be updated by the algorithm. Default is temporary',
action='store_true',
)
parser.add_argument(
'--lock',
help=
'sets override_type to lock. Scores won\'t be updated by the algorithm for three months. Default is '
'temporary',
action='store_true',
)
parser.add_argument(
'--no-bulk',
help=
'force an api call for each threats, useful to retrieve the details of threats created',
action='store_true',
)
if override_args:
args = parser.parse_args(override_args)
else:
args = parser.parse_args()
logger.debug(f'START: add_new_threats.py')
if not args.threat_types and not args.whitelist:
parser.error(
"threat types is required if the atom is not for whitelisting")
if args.permanent and args.lock:
parser.error("Only one override type is authorized")
if args.permanent:
override_type = OverrideType.PERMANENT
elif args.lock:
override_type = OverrideType.LOCK
else:
override_type = OverrideType.TEMPORARY
if args.is_csv:
try:
list_new_threats = load_csv(args.input, args.delimiter,
args.column - 1)
except ValueError as ve:
logger.error(ve)
exit()
else:
list_new_threats = load_list(args.input)
if not list_new_threats:
raise parser.error('No atom found in the input file.')
list_new_threats = defang_threats(list_new_threats, args.atom_type)
list_new_threats = list(OrderedDict.fromkeys(
list_new_threats)) # removing duplicates while preserving order
args.threat_types = flatten_list(args.threat_types)
threat_types = parse_threat_types(args.threat_types)
atom_type = AtomType[args.atom_type.upper()]
dtl = Datalake(env=args.env, log_level=args.loglevel)
spinner = Halo(text=f'Creating threats', spinner='dots')
spinner.start()
threat_response = dtl.Threats.add_threats(list_new_threats, atom_type,
threat_types, override_type,
args.whitelist, args.public,
args.tag, args.link,
args.no_bulk)
spinner.stop()
terminal_size = Endpoint._get_terminal_size()
if args.no_bulk:
for threat in threat_response:
logger.info(
f'{threat["hashkey"].ljust(terminal_size - 6, " ")} \x1b[0;30;42m OK \x1b[0m'
)
else:
failed = []
failed_counter = 0
created_counter = 0
for batch_res in threat_response:
failed.extend(batch_res['failed'])
for success in batch_res['success']:
for val_created in success['created_atom_values']:
created_counter += 1
logger.info(
f'{val_created.ljust(terminal_size - 6, " ")} \x1b[0;30;42m OK \x1b[0m'
)
for failed_obj in failed:
for failed_atom_val in failed_obj['failed_atom_values']:
failed_counter += 1
logger.info(
f'Creation failed for value {failed_atom_val.ljust(terminal_size - 6, " ")} \x1b[0;30;4\
1m KO \x1b[0m')
logger.info(
f'Number of batches: {len(threat_response)}\nCreated threats: {created_counter}\nFailed threat creation: {failed_counter}'
)
if args.output:
save_output(args.output, threat_response)
logger.debug(f'Results saved in {args.output}\n')
logger.debug(f'END: add_new_threats.py')
def main(override_args=None):
# Load initial args
parser = BaseScripts.start('Submit a new threat to Datalake from a file')
required_named = parser.add_argument_group('required arguments')
csv_control = parser.add_argument_group('CSV control arguments')
parser.add_argument(
'threats',
help='threats to lookup',
nargs='*',
)
parser.add_argument(
'-i',
'--input',
help='read threats to add from FILE',
)
parser.add_argument(
'-td',
'--threat_details',
action='store_true',
help='set if you also want to have access to the threat details ',
)
parser.add_argument(
'-ot',
'--output_type',
default='json',
help=
'set to the output type desired {json,csv}. Default is json if not specified',
)
required_named.add_argument(
'-a',
'--atom_type',
help='set it to define the atom type',
required=True,
)
csv_control.add_argument(
'--is_csv',
help='set if the file input is a CSV',
action='store_true',
)
csv_control.add_argument(
'-d',
'--delimiter',
help='set the delimiter of the CSV file',
default=',',
)
csv_control.add_argument(
'-c',
'--column',
help='select column of the CSV file, starting at 1',
type=int,
default=1,
)
if override_args:
args = parser.parse_args(override_args)
else:
args = parser.parse_args()
logger.debug(f'START: lookup_threats.py')
if not args.threats and not args.input:
parser.error("either a threat or an input_file is required")
if args.output_type:
try:
args.output_type = BaseEngine.output_type2header(args.output_type)
except ParserError as e:
logger.exception(
f'Exception raised while getting output type from headers # {str(e)}',
exc_info=False)
exit(1)
hashkey_only = not args.threat_details
dtl = Datalake(env=args.env, log_level=args.loglevel)
list_threats = list(args.threats) if args.threats else []
if args.input:
if args.is_csv:
try:
list_threats = list_threats + load_csv(
args.input, args.delimiter, args.column - 1)
except ValueError as ve:
logger.error(ve)
exit()
else:
list_threats = list_threats + load_list(args.input)
full_response = {}
atom_type = parse_atom_type_or_exit(args.atom_type)
list_threats = list(OrderedDict.fromkeys(
list_threats)) # removing duplicates while preserving order
for threat in list_threats:
response = dtl.Threats.lookup(threat,
atom_type=atom_type,
hashkey_only=hashkey_only)
found = response.get('threat_found', True)
text, color = boolean_to_text_and_color[found]
logger.info('{}{} hashkey:{} {}\x1b[0m'.format(color, threat,
response['hashkey'],
text))
full_response[threat] = response
if args.output:
if args.output_type == 'text/csv':
full_response = CsvBuilder.create_look_up_csv(
full_response,
args.atom_type,
has_details=args.threat_details,
)
save_output(args.output, full_response)
logger.debug(f'Results saved in {args.output}\n')
logger.debug(f'END: lookup_threats.py')
def main(override_args=None):
"""Method to start the script"""
logger.debug(f'START: get_threats_from_query_hash.py')
# Load initial args
parser = BaseScripts.start(
'Retrieve a list of response from a given query hash.')
parser.add_argument(
'--query_fields',
help=
'fields to be retrieved from the threat (default: only the hashkey)\n'
'If an atom detail isn\'t present in a particular atom, empty string is returned.',
nargs='+',
default=['threat_hashkey'],
)
parser.add_argument(
'--list',
help=
'Turn the output in a list (require query_fields to be a single element)',
action='store_true',
)
required_named = parser.add_argument_group('required arguments')
required_named.add_argument(
'query_hash',
help=
'the query hash from which to retrieve the response hashkeys or a path to the query body json file',
)
if override_args:
args = parser.parse_args(override_args)
else:
args = parser.parse_args()
configure_logging(args.loglevel)
if len(args.query_fields) > 1 and args.list:
parser.error(
"List output format is only available if a single element is queried (via query_fields)"
)
query_body = {}
query_hash = args.query_hash
if len(query_hash) != 32 or os.path.exists(query_hash):
try:
with open(query_hash, 'r') as query_body_file:
query_body = json.load(query_body_file)
except FileNotFoundError:
logger.error(
f"Couldn't understand the given value as a query hash or path to query body: {query_hash}"
)
exit(1)
# Load api_endpoints and tokens
dtl = Datalake(env=args.env, log_level=args.loglevel)
logger.debug(
f'Start to search for threat from the query hash:{query_hash}')
spinner = None
if logger.isEnabledFor(logging.INFO):
spinner = Halo(text=f'Creating bulk task', spinner='dots')
spinner.start()
task = dtl.BulkSearch.create_task(query_body=query_body,
query_hash=query_hash,
query_fields=args.query_fields)
if spinner:
spinner.text = f'Waiting for bulk task {task.uuid} response'
response = task.download_sync()
original_count = response.get('count', 0)
if spinner:
spinner.succeed()
spinner.info(
f'Number of threat that have been retrieved: {original_count}')
formatted_output = format_output(response, args.list)
if args.output:
with open(args.output, 'w') as output:
output.write(formatted_output)
else:
logger.info(formatted_output)
if args.output:
logger.info(f'Threats saved in {args.output}')
else:
logger.info('Done')
def main(override_args=None):
parser = BaseScripts.start(
'Gets threats from given query body or query hash.',
output_file_required=True)
parser.add_argument('-i',
'--input',
help='read query body from a json file')
parser.add_argument('--query-hash',
help='sets the query hash for the advanced search')
parser.add_argument(
'-l',
'--limit',
help=
'defines how many items will be returned in one page slice. Accepted values: 0 to 5000, default is 20',
type=int,
default=20)
parser.add_argument(
'--offset',
help=
'defines an index of the first requested item. Accepted values: 0 and bigger, default is 0.',
type=int,
default=0)
parser.add_argument(
'-ot',
'--output-type',
help=
'sets the output type desired {json, csv, stix, misp}. Default is json',
default='json')
parser.add_argument(
'--ordering',
help=
'threat field to filter on. To sort the results by relevance (if any "search" is applied), just skip '
'this field. To use the reversed order, use minus, i.e. --ordering="-last_updated" in your command line.'
)
if override_args:
args = parser.parse_args(override_args)
else:
args = parser.parse_args()
logger.debug(f'START: advanced_search.py')
if bool(args.input) == bool(args.query_hash):
raise ValueError(
'Either an input file with a query body or a query hash needs to be provided.'
)
try:
output_type = Output[args.output_type.upper()]
except KeyError:
logger.error(
'Not supported output, please use json, stix, misp or csv')
exit(1)
dtl = Datalake(env=args.env, log_level=args.loglevel)
if args.input:
query_body = load_json(args.input)
resp = dtl.AdvancedSearch.advanced_search_from_query_body(
query_body,
limit=args.limit,
offset=args.offset,
output=output_type,
ordering=args.ordering)
else:
resp = dtl.AdvancedSearch.advanced_search_from_query_hash(
args.query_hash,
limit=args.limit,
offset=args.offset,
output=output_type,
ordering=args.ordering)
save_output(args.output, resp)
logger.info(
f'\x1b[0;30;42m OK: MATCHING THREATS SAVED IN {args.output} \x1b[0m')
logger.debug(f'END: advanced_search.py')
def main(override_args=None):
"""Method to start the script"""
# Load initial args
parser = BaseScripts.start(
'Edit scores of a specified list of ids (hashkeys)')
parser.add_argument(
'hashkeys',
help='hashkeys of the threat to edit score.',
nargs='*',
)
parser.add_argument(
'-i',
'--input_file',
help='hashkey txt file, with one hashkey by line.',
)
parser.add_argument(
'-t',
'--threat_types',
nargs='+',
help=
'choose specific threat types and their score, like: ddos 50 scam 15',
default=[],
action='append',
)
parser.add_argument(
'-w',
'--whitelist',
help=
'Whitelist the input, equivalent to setting all threat types at 0.',
action='store_true',
)
parser.add_argument(
'--permanent',
help=
'''Permanent: all values will override any values provided by both newer and
older IOCs. Newer IOCs with override_type permanent can still override old permanent changes.
temporary: all values should override any values provided by older IOCs,
but not newer ones.''',
action='store_true',
)
parser.add_argument(
'--lock',
help=
'sets override_type to lock. Scores won\'t be updated by the algorithm for three months. Default is '
'temporary',
action='store_true',
)
if override_args:
args = parser.parse_args(override_args)
else:
args = parser.parse_args()
logger.debug(f'START: edit_score.py')
if not args.hashkeys and not args.input_file:
parser.error("either a hashkey or an input_file is required")
if args.permanent and args.lock:
parser.error("Only one override type is authorized")
if args.permanent:
override_type = OverrideType.PERMANENT
elif args.lock:
override_type = OverrideType.LOCK
else:
override_type = OverrideType.TEMPORARY
if args.whitelist:
parsed_threat_type = get_whitelist_threat_types()
else:
args.threat_types = flatten_list(args.threat_types)
if not args.threat_types or len(args.threat_types) % 2 != 0:
parser.error(
"threat_types invalid ! should be like: ddos 50 scam 15")
parsed_threat_type = parse_threat_types(args.threat_types)
# removing duplicates while preserving order
hashkeys = args.hashkeys
if args.input_file:
retrieve_hashkeys_from_file(args.input_file, hashkeys)
if not hashkeys:
raise parser.error('No hashkey found in the input file.')
hashkeys_chunks = list(
split_list(
list(OrderedDict.fromkeys(hashkeys)) if hashkeys else [], 100))
dtl = Datalake(env=args.env, log_level=args.loglevel)
response_list = []
for index, hashkeys in enumerate(hashkeys_chunks):
try:
dtl.Threats.edit_score_by_hashkeys(hashkeys, parsed_threat_type,
override_type)
except ValueError as e:
logger.warning(
f'\x1b[6;30;41mBATCH {str(index+1)}/{len(list(hashkeys_chunks))}: FAILED\x1b[0m'
)
for hashkey in hashkeys:
response_list.append(hashkey + ': FAILED')
logger.warning(f'\x1b[6;30;41m{hashkey} : FAILED\x1b[0m')
logger.warning(e)
else:
logger.info(
f'\x1b[6;30;42mBATCH {str(index+1)}/{len(list(hashkeys_chunks))}: OK\x1b[0m'
)
for hashkey in hashkeys:
response_list.append(hashkey + ': OK')
if args.output:
save_output(args.output, response_list)
logger.info(f'Results saved in {args.output}\n')
logger.debug(f'END: edit_score.py')