-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathprocess_email.py
1291 lines (988 loc) · 48.7 KB
/
process_email.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# File: process_email.py
#
# Copyright (c) 2016-2024 Splunk Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software distributed under
# the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
# either express or implied. See the License for the specific language governing permissions
# and limitations under the License.
import base64
import email
import hashlib
import json
import mimetypes
import os
import re
import shutil
import socket
import tempfile
from builtins import object, str
from collections import OrderedDict
from copy import deepcopy
from email.header import decode_header, make_header
from html import unescape
import magic
import phantom.app as phantom
import phantom.rules as phantom_rules
import phantom.utils as ph_utils
from bs4 import BeautifulSoup, UnicodeDammit
from django.core.validators import URLValidator
from requests.structures import CaseInsensitiveDict
_container_common = {"run_automation": False} # Don't run any playbooks, when this artifact is added
_artifact_common = {"run_automation": False} # Don't run any playbooks, when this artifact is added
FILE_EXTENSIONS = {
".vmsn": ["os memory dump", "vm snapshot file"],
".vmss": ["os memory dump", "vm suspend file"],
".js": ["javascript"],
".doc": ["doc"],
".docx": ["doc"],
".xls": ["xls"],
".xlsx": ["xls"],
}
MAGIC_FORMATS = [
(re.compile("^PE.* Windows"), ["pe file", "hash"]),
(re.compile("^MS-DOS executable"), ["pe file", "hash"]),
(re.compile("^PDF "), ["pdf"]),
(re.compile("^MDMP crash"), ["process dump"]),
(re.compile("^Macromedia Flash"), ["flash"]),
]
EWS_DEFAULT_ARTIFACT_COUNT = 100
EWS_DEFAULT_CONTAINER_COUNT = 100
HASH_FIXED_PHANTOM_VERSION = "2.0.201"
OFFICE365_APP_ID = "a73f6d32-c9d5-4fec-b024-43876700daa6"
EXCHANGE_ONPREM_APP_ID = "badc5252-4a82-4a6d-bc53-d1e503857124"
IMAP_APP_ID = "9f2e9f72-b0e5-45d6-92a7-09ef820476c1"
PROC_EMAIL_JSON_FILES = "files"
PROC_EMAIL_JSON_BODIES = "bodies"
PROC_EMAIL_JSON_DATE = "date"
PROC_EMAIL_JSON_FROM = "from"
PROC_EMAIL_JSON_SUBJECT = "subject"
PROC_EMAIL_JSON_TO = "to"
PROC_EMAIL_JSON_START_TIME = "start_time"
PROC_EMAIL_JSON_EXTRACT_ATTACHMENTS = "extract_attachments"
PROC_EMAIL_JSON_EXTRACT_BODY = "add_body_to_header_artifacts"
PROC_EMAIL_JSON_EXTRACT_URLS = "extract_urls"
PROC_EMAIL_JSON_EXTRACT_IPS = "extract_ips"
PROC_EMAIL_JSON_EXTRACT_DOMAINS = "extract_domains"
PROC_EMAIL_JSON_EXTRACT_HASHES = "extract_hashes"
PROC_EMAIL_JSON_IPS = "ips"
PROC_EMAIL_JSON_HASHES = "hashes"
PROC_EMAIL_JSON_URLS = "urls"
PROC_EMAIL_JSON_DOMAINS = "domains"
PROC_EMAIL_JSON_MSG_ID = "message_id"
PROC_EMAIL_JSON_EMAIL_HEADERS = "email_headers"
PROC_EMAIL_CONTENT_TYPE_MESSAGE = "message/rfc822"
URI_REGEX = r"[Hh][Tt][Tt][Pp][Ss]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+#]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
EMAIL_REGEX = r"\b[A-Z0-9._%+-]+@+[A-Z0-9.-]+\.[A-Z]{2,}\b"
EMAIL_REGEX2 = r'".*"@[A-Z0-9.-]+\.[A-Z]{2,}\b'
HASH_REGEX = r"\b[0-9a-fA-F]{32}\b|\b[0-9a-fA-F]{40}\b|\b[0-9a-fA-F]{64}\b"
IP_REGEX = r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}"
IPV6_REGEX = r"\s*((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|"
IPV6_REGEX += r"(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}"
IPV6_REGEX += r"|((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))"
IPV6_REGEX += r"|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})"
IPV6_REGEX += r"|:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3})|:))|"
IPV6_REGEX += r"(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})"
IPV6_REGEX += r"|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|"
IPV6_REGEX += r"(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})"
IPV6_REGEX += r"|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|"
IPV6_REGEX += r"(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})"
IPV6_REGEX += r"|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|"
IPV6_REGEX += r"(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})"
IPV6_REGEX += r"|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:))|"
IPV6_REGEX += r"(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\d|1\d\d"
IPV6_REGEX += r"|[1-9]?\d)(\.(25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)){3}))|:)))(%.+)?\s*"
uri_regexc = re.compile(URI_REGEX)
email_regexc = re.compile(EMAIL_REGEX, re.IGNORECASE)
email_regexc2 = re.compile(EMAIL_REGEX2, re.IGNORECASE)
hash_regexc = re.compile(HASH_REGEX)
ip_regexc = re.compile(IP_REGEX)
ipv6_regexc = re.compile(IPV6_REGEX)
class ProcessEmail(object):
def __init__(self):
self._base_connector = None
self._config = dict()
self._email_id_contains = list()
self._container = dict()
self._artifacts = list()
self._attachments = list()
self._headers_from_ews = list()
self._attachments_from_ews = list()
self._parsed_mail = None
self._guid_to_hash = dict()
self._tmp_dirs = list()
def _get_file_contains(self, file_path):
contains = []
ext = os.path.splitext(file_path)[1]
contains.extend(FILE_EXTENSIONS.get(ext, []))
magic_str = magic.from_file(file_path)
for regex, cur_contains in MAGIC_FORMATS:
if regex.match(magic_str):
contains.extend(cur_contains)
return contains
def _is_ip(self, input_ip):
if ph_utils.is_ip(input_ip):
return True
if self.is_ipv6(input_ip):
return True
return False
def is_ipv6(self, input_ip):
try:
socket.inet_pton(socket.AF_INET6, input_ip)
except Exception: # not a valid v6 address
return False
return True
def _debug_print(self, *args):
if self._base_connector and (hasattr(self._base_connector, "debug_print")):
self._base_connector.debug_print(*args)
return
def _clean_url(self, url):
url = url.strip(">),.]\r\n")
# Check before splicing, find returns -1 if not found
# _and_ you will end up splicing on -1 (incorrectly)
if "<" in url:
url = url[: url.find("<")]
if ">" in url:
url = url[: url.find(">")]
url = url.rstrip("]")
return url.strip()
def _extract_urls_domains(self, file_data, urls, domains):
if (not self._config[PROC_EMAIL_JSON_EXTRACT_DOMAINS]) and (not self._config[PROC_EMAIL_JSON_EXTRACT_URLS]):
return
# try to load the email
try:
soup = BeautifulSoup(file_data, "html.parser")
except Exception as e:
error_code, error_msg = self._base_connector._get_error_message_from_exception(e)
err = "Error Code: {0}. Error Message: {1}".format(error_code, error_msg)
self._debug_print("Error occurred while extracting domains of the URLs. {0}".format(err))
return
uris = []
# get all tags that have hrefs and srcs
links = soup.find_all(href=True)
srcs = soup.find_all(src=True)
if links or srcs:
uri_text = []
if links:
for x in links:
# work on the text part of the link, they might be http links different from the href
# and were either missed by the uri_regexc while parsing text or there was no text counterpart
# in the email
uri_text.append(self._clean_url(x.get_text()))
# it's html, so get all the urls
if not x["href"].startswith("mailto:"):
uris.append(x["href"])
if srcs:
for x in srcs:
uri_text.append(self._clean_url(x.get_text()))
# it's html, so get all the urls
uris.append(x["src"])
if uri_text:
uri_text = [x for x in uri_text if x.startswith("http")]
if uri_text:
uris.extend(uri_text)
else:
# To unescape html escaped body
file_data = unescape(file_data)
# Parse it as a text file
uris = re.findall(uri_regexc, file_data)
if uris:
uris = [self._clean_url(x) for x in uris]
validate_url = URLValidator(schemes=["http", "https"])
validated_urls = list()
for url in uris:
try:
validate_url(url)
validated_urls.append(url)
except Exception:
pass
if self._config[PROC_EMAIL_JSON_EXTRACT_URLS]:
# add the uris to the urls
urls |= set(validated_urls)
if self._config[PROC_EMAIL_JSON_EXTRACT_DOMAINS]:
for uri in validated_urls:
domain = phantom.get_host_from_url(uri)
if domain and (not self._is_ip(domain)):
domains.add(domain)
# work on any mailto urls if present
if links:
mailtos = [x["href"] for x in links if (x["href"].startswith("mailto:"))]
for curr_email in mailtos:
domain = curr_email[curr_email.find("@") + 1 :]
if domain and (not self._is_ip(domain)):
if "?" in domain:
domain = domain[: domain.find("?")]
domains.add(domain)
return
def _get_ips(self, file_data, ips):
# First extract what looks like an IP from the file, this is a faster operation
ips_in_mail = re.findall(ip_regexc, file_data)
ip6_in_mail = re.findall(ipv6_regexc, file_data)
if ip6_in_mail:
for ip6_tuple in ip6_in_mail:
ip6s = [x for x in ip6_tuple if x]
ips_in_mail.extend(ip6s)
# Now validate them
if ips_in_mail:
ips_in_mail = set(ips_in_mail)
# match it with a slower and difficult regex.
# TODO: Fix this with a one step approach.
ips_in_mail = [x for x in ips_in_mail if self._is_ip(x)]
if ips_in_mail:
ips |= set(ips_in_mail)
def _handle_body(self, body, parsed_mail, body_index, email_id):
local_file_path = body["file_path"]
charset = body.get("charset")
ips = parsed_mail[PROC_EMAIL_JSON_IPS]
hashes = parsed_mail[PROC_EMAIL_JSON_HASHES]
urls = parsed_mail[PROC_EMAIL_JSON_URLS]
domains = parsed_mail[PROC_EMAIL_JSON_DOMAINS]
file_data = None
try:
with open(local_file_path, "r") as f:
file_data = f.read()
except Exception:
with open(local_file_path, "rb") as f:
file_data = f.read()
if (file_data is None) or (len(file_data) == 0):
return phantom.APP_ERROR
file_data = UnicodeDammit(file_data).unicode_markup.encode("utf-8").decode("utf-8")
self._parse_email_headers_as_inline(file_data, parsed_mail, charset, email_id)
if self._config[PROC_EMAIL_JSON_EXTRACT_DOMAINS]:
emails = []
emails.extend(re.findall(email_regexc, file_data))
emails.extend(re.findall(email_regexc2, file_data))
for curr_email in emails:
domain = curr_email[curr_email.rfind("@") + 1 :]
if domain and (not ph_utils.is_ip(domain)):
domains.add(domain)
self._extract_urls_domains(file_data, urls, domains)
if self._config[PROC_EMAIL_JSON_EXTRACT_IPS]:
self._get_ips(file_data, ips)
if self._config[PROC_EMAIL_JSON_EXTRACT_HASHES]:
hashs_in_mail = re.findall(hash_regexc, file_data)
if hashs_in_mail:
hashes |= set(hashs_in_mail)
return phantom.APP_SUCCESS
def _add_artifacts(self, cef_key, input_set, artifact_name, start_index, artifacts):
added_artifacts = 0
for entry in input_set:
# ignore empty entries
if not entry:
continue
artifact = {}
artifact.update(_artifact_common)
artifact["source_data_identifier"] = start_index + added_artifacts
artifact["cef"] = {cef_key: entry}
artifact["name"] = artifact_name
self._debug_print("Artifact:", artifact)
artifacts.append(artifact)
added_artifacts += 1
return added_artifacts
def _parse_email_headers_as_inline(self, file_data, parsed_mail, charset, email_id):
# remove the 'Forwarded Message' from the email text and parse it
p = re.compile(r".*Forwarded Message.*\r\n(.*)", re.IGNORECASE)
email_text = p.sub(r"\1", file_data.strip())
mail = email.message_from_string(email_text)
# Get the array
# email_headers = parsed_mail[PROC_EMAIL_JSON_EMAIL_HEADERS]
self._parse_email_headers(parsed_mail, mail, charset, add_email_id=email_id)
# email_headers.append(mail.items())
return phantom.APP_SUCCESS
def _add_email_header_artifacts(self, email_header_artifacts, start_index, artifacts):
added_artifacts = 0
for artifact in email_header_artifacts:
artifact["source_data_identifier"] = start_index + added_artifacts
artifacts.append(artifact)
added_artifacts += 1
return added_artifacts
def _create_artifacts(self, parsed_mail):
# get all the artifact data in their own list objects
ips = parsed_mail[PROC_EMAIL_JSON_IPS]
hashes = parsed_mail[PROC_EMAIL_JSON_HASHES]
urls = parsed_mail[PROC_EMAIL_JSON_URLS]
domains = parsed_mail[PROC_EMAIL_JSON_DOMAINS]
email_headers = parsed_mail[PROC_EMAIL_JSON_EMAIL_HEADERS]
# set the default artifact dict
artifact_id = 0
# add artifacts
added_artifacts = self._add_artifacts("sourceAddress", ips, "IP Artifact", artifact_id, self._artifacts)
artifact_id += added_artifacts
added_artifacts = self._add_artifacts("fileHash", hashes, "Hash Artifact", artifact_id, self._artifacts)
artifact_id += added_artifacts
added_artifacts = self._add_artifacts("requestURL", urls, "URL Artifact", artifact_id, self._artifacts)
artifact_id += added_artifacts
# domains = [x.decode('idna') for x in domains]
added_artifacts = self._add_artifacts("destinationDnsDomain", domains, "Domain Artifact", artifact_id, self._artifacts)
artifact_id += added_artifacts
added_artifacts = self._add_email_header_artifacts(email_headers, artifact_id, self._artifacts)
artifact_id += added_artifacts
return phantom.APP_SUCCESS
def _decode_uni_string(self, input_str, def_name):
# try to find all the decoded strings, we could have multiple decoded strings
# or a single decoded string between two normal strings separated by \r\n
# YEAH...it could get that messy
encoded_strings = re.findall(r"=\?.*?\?=", input_str, re.I)
# return input_str as is, no need to do any conversion
if not encoded_strings:
return input_str
# get the decoded strings
try:
decoded_strings = [decode_header(x)[0] for x in encoded_strings]
decoded_strings = [{"value": x[0], "encoding": x[1]} for x in decoded_strings]
except Exception as e:
error_code, error_msg = self._base_connector._get_error_message_from_exception(e)
err = "Error Code: {0}. Error Message: {1}".format(error_code, error_msg)
self._debug_print("Decoding: {0}. {1}".format(encoded_strings, err))
return def_name
# convert to dict for safe access, if it's an empty list, the dict will be empty
decoded_strings = dict(enumerate(decoded_strings))
new_str = ""
new_str_create_count = 0
for i, encoded_string in enumerate(encoded_strings):
decoded_string = decoded_strings.get(i)
if not decoded_string:
# nothing to replace with
continue
value = decoded_string.get("value")
encoding = decoded_string.get("encoding")
if not encoding or not value:
# nothing to replace with
continue
try:
if encoding != "utf-8":
value = str(value, encoding)
except Exception:
pass
try:
# commenting the existing approach due to a new approach being deployed below
# substitute the encoded string with the decoded one
# input_str = input_str.replace(encoded_string, value)
# make new string instead of replacing in the input string because issue find in PAPP-9531
if value:
new_str += UnicodeDammit(value).unicode_markup
new_str_create_count += 1
except Exception:
pass
# replace input string with new string because issue find in PAPP-9531
if new_str and new_str_create_count == len(encoded_strings):
self._debug_print("Creating a new string entirely from the encoded_strings and assiging into input_str")
input_str = new_str
return input_str
def _get_container_name(self, parsed_mail, email_id):
# Create the default name
def_cont_name = "Email ID: {0}".format(email_id)
# get the subject from the parsed mail
subject = parsed_mail.get(PROC_EMAIL_JSON_SUBJECT)
# if no subject then return the default
if not subject:
return def_cont_name
try:
return str(make_header(decode_header(subject)))
except Exception:
return self._decode_uni_string(subject, def_cont_name)
def _handle_if_body(self, content_disp, content_id, content_type, part, bodies, file_path):
process_as_body = False
# if content disposition is None then assume that it is
if content_disp is None:
process_as_body = True
# if content disposition is inline
elif content_disp.lower().strip() == "inline":
if ("text/html" in content_type) or ("text/plain" in content_type):
process_as_body = True
if not process_as_body:
return phantom.APP_SUCCESS, True
part_payload = part.get_payload(decode=True)
if not part_payload:
return phantom.APP_SUCCESS, False
with open(file_path, "wb") as f:
f.write(part_payload)
bodies.append({"file_path": file_path, "charset": part.get_content_charset()})
return phantom.APP_SUCCESS, False
def remove_child_info(self, file_path):
if file_path.endswith("_True"):
return file_path.rstrip("_True")
else:
return file_path.rstrip("_False")
def _handle_attachment(self, part, file_name, file_path):
files = self._parsed_mail[PROC_EMAIL_JSON_FILES]
if not self._config[PROC_EMAIL_JSON_EXTRACT_ATTACHMENTS]:
return phantom.APP_SUCCESS
part_base64_encoded = part.get_payload()
headers = self._get_email_headers_from_part(part)
attach_meta_info = dict()
if headers:
attach_meta_info = {"headers": dict(headers)}
for curr_attach in self._attachments_from_ews:
if curr_attach.get("should_ignore", False):
continue
try:
attach_content = curr_attach["content"]
except Exception:
continue
if attach_content.strip().replace("\r\n", "") == part_base64_encoded.strip().replace("\r\n", ""):
attach_meta_info.update(dict(curr_attach))
del attach_meta_info["content"]
curr_attach["should_ignore"] = True
part_payload = part.get_payload(decode=True)
if not part_payload:
return phantom.APP_SUCCESS
try:
with open(file_path, "wb") as f:
f.write(part_payload)
except IOError as e:
error_code, error_msg = self._base_connector._get_error_message_from_exception(e)
try:
if "File name too long" in error_msg:
new_file_name = "ph_long_file_name_temp"
file_path = "{}{}".format(
self.remove_child_info(file_path).rstrip(file_name.replace("<", "").replace(">", "").replace(" ", "")), new_file_name
)
self._debug_print("Original filename: {}".format(file_name))
self._debug_print("Modified filename: {}".format(new_file_name))
with open(file_path, "wb") as long_file:
long_file.write(part_payload)
else:
self._debug_print("Error occurred while adding file to Vault. Error Details: {}".format(error_msg))
return
except Exception as e:
error_code, error_msg = self._base_connector._get_error_message_from_exception(e)
self._debug_print("Error occurred while adding file to Vault. Error Details: {}".format(error_msg))
return
except Exception as e:
error_code, error_msg = self._base_connector._get_error_message_from_exception(e)
self._debug_print("Error occurred while adding file to Vault. Error Details: {}".format(error_msg))
return
files.append({"file_name": file_name, "file_path": file_path, "meta_info": attach_meta_info})
def _handle_part(self, part, part_index, tmp_dir, extract_attach, parsed_mail):
bodies = parsed_mail[PROC_EMAIL_JSON_BODIES]
# get the file_name
file_name = part.get_filename()
content_disp = part.get("Content-Disposition")
content_type = part.get("Content-Type")
content_id = part.get("Content-ID")
if file_name is None:
# init name and extension to default values
name = "part_{0}".format(part_index)
extension = ".{0}".format(part_index)
# Try to create an extension from the content type if possible
if content_type is not None:
extension = mimetypes.guess_extension(re.sub(";.*", "", content_type))
# Try to create a name from the content id if possible
if content_id is not None:
name = content_id
file_name = "{0}{1}".format(name, extension)
else:
file_name = self._decode_uni_string(file_name, file_name)
# Remove any chars that we don't want in the name
file_path = "{0}/{1}_{2}".format(tmp_dir, part_index, file_name.translate(file_name.maketrans("", "", "".join(["<", ">", " "]))))
self._debug_print("file_path: {0}".format(file_path))
# is the part representing the body of the email
status, process_further = self._handle_if_body(content_disp, content_id, content_type, part, bodies, file_path)
if not process_further:
return phantom.APP_SUCCESS
# is this another email as an attachment
if (content_type is not None) and (content_type.find(PROC_EMAIL_CONTENT_TYPE_MESSAGE) != -1):
return phantom.APP_SUCCESS
# This is an attachment and it's not an email
self._handle_attachment(part, file_name, file_path)
return phantom.APP_SUCCESS
def _update_headers(self, headers):
# compare the various values of the passed header (param: headers)
# to the header that the class got self._headers_from_ews
if not self._headers_from_ews:
return phantom.APP_SUCCESS
if not headers:
return phantom.APP_SUCCESS
headers_ci = CaseInsensitiveDict(headers)
for curr_header_lower in self._headers_from_ews:
if headers_ci.get("message-id", "default_value1").strip() == curr_header_lower.get("message-id", "default_value2").strip():
# the headers match with the one that we got from the ews API, so update it
headers.update(curr_header_lower)
return phantom.APP_SUCCESS
def _get_email_headers_from_part(self, part, charset=None):
email_headers = list(part.items())
if not email_headers:
return {}
# Convert the header tuple into a dictionary
headers = CaseInsensitiveDict()
[headers.update({x[0]: x[1]}) for x in email_headers]
# Handle received separately
received_headers = [x[1] for x in email_headers if x[0].lower() == "received"]
if received_headers:
headers["Received"] = received_headers
# handle the subject string, if required add a new key
subject = headers.get("Subject")
if subject:
try:
headers["decodedSubject"] = str(make_header(decode_header(subject)))
except Exception:
headers["decodedSubject"] = self._decode_uni_string(subject, subject)
to_data = headers.get("To")
if to_data:
headers["decodedTo"] = self._decode_uni_string(to_data, to_data)
from_data = headers.get("From")
if from_data:
headers["decodedFrom"] = self._decode_uni_string(from_data, from_data)
cc_data = headers.get("CC")
if cc_data:
headers["decodedCC"] = self._decode_uni_string(cc_data, cc_data)
return headers
def _parse_email_headers(self, parsed_mail, part, charset=None, add_email_id=None):
email_header_artifacts = parsed_mail[PROC_EMAIL_JSON_EMAIL_HEADERS]
headers = self._get_email_headers_from_part(part, charset)
if not headers:
return 0
# Parse email keys first
cef_artifact = {}
cef_types = {}
if headers.get("From"):
emails = headers["From"]
if emails:
cef_artifact.update({"fromEmail": emails})
if headers.get("To"):
emails = headers["To"]
if emails:
cef_artifact.update({"toEmail": emails})
# if the header did not contain any email addresses then ignore this artifact
message_id = headers.get("message-id")
if (not cef_artifact) and (message_id is None):
return 0
cef_types.update({"fromEmail": ["email"], "toEmail": ["email"]})
if headers:
self._update_headers(headers)
cef_artifact["emailHeaders"] = dict(headers)
body = None
body_key = None
for curr_key in list(cef_artifact["emailHeaders"].keys()):
if curr_key.lower().startswith("body"):
body = cef_artifact["emailHeaders"].pop(curr_key)
body_key = None
elif curr_key == "parentInternetMessageId":
curr_value = cef_artifact["emailHeaders"].pop(curr_key)
cef_artifact.update({curr_key: curr_value})
elif curr_key == "parentGuid":
curr_value = cef_artifact["emailHeaders"].pop(curr_key)
cef_artifact.update({curr_key: curr_value})
elif curr_key == "emailGuid":
curr_value = cef_artifact["emailHeaders"].pop(curr_key)
cef_artifact.update({curr_key: curr_value})
if self._config.get(PROC_EMAIL_JSON_EXTRACT_BODY, False):
if body: # Body was already added to headers (through exchange API?)
cef_artifact.update({body_key, body})
else:
queue = list()
queue.append(part)
i = 1
while len(queue) > 0:
cur_part = queue.pop(0)
# If the part is a multipart message, get_payload returns a list of parts
# Else it returns the body
payload = cur_part.get_payload()
if isinstance(payload, list):
queue.extend(payload)
else:
encoding = cur_part["Content-Transfer-Encoding"]
if encoding:
if "base64" in encoding.lower():
payload = base64.b64decode("".join(payload.splitlines()))
elif encoding != "8bit":
payload = cur_part.get_payload(decode=True)
payload = UnicodeDammit(payload).unicode_markup.encode("utf-8").decode("utf-8")
try:
json.dumps({"body": payload})
except TypeError: # py3
try:
payload = payload.decode("UTF-8")
except UnicodeDecodeError:
self._debug_print("Email body caused unicode exception. Encoding as base64.")
# payload = base64.b64encode(payload)
payload = base64.b64encode(payload).decode("UTF-8")
cef_artifact["body_base64encoded"] = True
except UnicodeDecodeError:
self._debug_print("Email body caused unicode exception. Encoding as base64.")
payload = base64.b64encode(payload)
cef_artifact["body_base64encoded"] = True
cef_artifact.update({"bodyPart{}".format(i): payload if payload else None})
cef_artifact.update({"bodyPart{}ContentType".format(i): cur_part["Content-Type"] if cur_part["Content-Type"] else None})
i += 1
# Adding the email id as a cef artifact crashes the UI when trying to show the action dialog box
# so not adding this right now. All the other code to process the emailId is there, but the refraining
# from adding the emailId
# add_email_id = False
if add_email_id:
cef_artifact["emailId"] = add_email_id
if self._email_id_contains:
cef_types.update({"emailId": self._email_id_contains})
artifact = {}
artifact.update(_artifact_common)
artifact["name"] = "Email Artifact"
artifact["cef"] = cef_artifact
artifact["cef_types"] = cef_types
email_header_artifacts.append(artifact)
return len(email_header_artifacts)
def _handle_mail_object(self, mail, email_id, rfc822_email, tmp_dir, start_time_epoch):
self._parsed_mail = OrderedDict()
# Create a tmp directory for this email, will extract all files here
tmp_dir = tmp_dir
if not os.path.exists(tmp_dir):
os.makedirs(tmp_dir)
extract_attach = self._config[PROC_EMAIL_JSON_EXTRACT_ATTACHMENTS]
# Extract fields and place it in a dictionary
self._parsed_mail[PROC_EMAIL_JSON_SUBJECT] = mail.get("Subject", "")
self._parsed_mail[PROC_EMAIL_JSON_FROM] = mail.get("From", "")
self._parsed_mail[PROC_EMAIL_JSON_TO] = mail.get("To", "")
self._parsed_mail[PROC_EMAIL_JSON_DATE] = mail.get("Date", "")
self._parsed_mail[PROC_EMAIL_JSON_MSG_ID] = mail.get("Message-ID", "")
self._parsed_mail[PROC_EMAIL_JSON_FILES] = files = []
self._parsed_mail[PROC_EMAIL_JSON_BODIES] = bodies = []
self._parsed_mail[PROC_EMAIL_JSON_START_TIME] = start_time_epoch
self._parsed_mail[PROC_EMAIL_JSON_EMAIL_HEADERS] = []
# parse the parts of the email
if mail.is_multipart():
for i, part in enumerate(mail.walk()):
add_email_id = None
if i == 0:
add_email_id = email_id
self._parse_email_headers(self._parsed_mail, part, add_email_id=add_email_id)
# parsed_mail[PROC_EMAIL_JSON_EMAIL_HEADERS].append(part.items())
# _debug_print("part: {0}".format(part.__dict__))
# _debug_print("part type", type(part))
if part.is_multipart():
continue
try:
ret_val = self._handle_part(part, i, tmp_dir, extract_attach, self._parsed_mail)
except Exception as e:
self._debug_print("ErrorExp in _handle_part # {0}".format(i), e)
continue
if phantom.is_fail(ret_val):
continue
else:
self._parse_email_headers(self._parsed_mail, mail, add_email_id=email_id)
# parsed_mail[PROC_EMAIL_JSON_EMAIL_HEADERS].append(mail.items())
file_path = "{0}/part_1.text".format(tmp_dir)
with open(file_path, "wb") as f:
f.write(mail.get_payload(decode=True))
bodies.append({"file_path": file_path, "charset": mail.get_content_charset()})
# get the container name
container_name = self._get_container_name(self._parsed_mail, email_id)
if container_name is None:
return phantom.APP_ERROR
# Add the container
# first save the container, to do that copy things from parsed_mail to a new object
container = {}
container_data = dict(self._parsed_mail)
# delete the header info, we dont make it a part of the container json
del container_data[PROC_EMAIL_JSON_EMAIL_HEADERS]
container.update(_container_common)
fips_enabled = self._base_connector._get_fips_enabled()
# if fips is not enabled, we should continue with our existing md5 usage for generating hashes
# to not impact existing customers
if not self._base_connector._is_hex:
try:
if not fips_enabled:
folder_hex = hashlib.md5(self._base_connector._folder_name)
else:
folder_hex = hashlib.sha256(self._base_connector._folder_name)
except Exception:
if not fips_enabled:
folder_hex = hashlib.md5(self._base_connector._folder_name.encode())
else:
folder_hex = hashlib.sha256(self._base_connector._folder_name.encode())
folder_sdi = folder_hex.hexdigest()
else:
folder_sdi = self._base_connector._folder_name
self._container["source_data_identifier"] = "{} : {}".format(folder_sdi, email_id)
self._container["name"] = container_name
self._container["data"] = {"raw_email": rfc822_email}
# Create the sets before handling the bodies If both the bodies add the same ip
# only one artifact should be created
self._parsed_mail[PROC_EMAIL_JSON_IPS] = set()
self._parsed_mail[PROC_EMAIL_JSON_HASHES] = set()
self._parsed_mail[PROC_EMAIL_JSON_URLS] = set()
self._parsed_mail[PROC_EMAIL_JSON_DOMAINS] = set()
# For bodies
for i, body in enumerate(bodies):
if not body:
continue
try:
self._handle_body(body, self._parsed_mail, i, email_id)
except Exception as e:
self._debug_print("ErrorExp in _handle_body # {0}: {1}".format(i, str(e)))
continue
# Files
self._attachments.extend(files)
self._create_artifacts(self._parsed_mail)
return phantom.APP_SUCCESS
def _set_email_id_contains(self, email_id):
if not self._base_connector:
return
email_id = str(email_id)
if (self._base_connector.get_app_id() == EXCHANGE_ONPREM_APP_ID) and (email_id.endswith("=")):
self._email_id_contains = ["exchange email id"]
elif (self._base_connector.get_app_id() == OFFICE365_APP_ID) and (email_id.endswith("=")):
self._email_id_contains = ["office 365 email id"]
elif (self._base_connector.get_app_id() == IMAP_APP_ID) and (email_id.isdigit()):
self._email_id_contains = ["imap email id"]
elif ph_utils.is_sha1(email_id):
self._email_id_contains = ["vault id"]
return
def _int_process_email(self, rfc822_email, email_id, start_time_epoch):
mail = email.message_from_string(rfc822_email)
ret_val = phantom.APP_SUCCESS
tmp_dir = tempfile.mkdtemp(prefix="ph_email_phimap")
self._tmp_dirs.append(tmp_dir)
try:
ret_val = self._handle_mail_object(mail, email_id, rfc822_email, tmp_dir, start_time_epoch)
except Exception as e:
message = "ErrorExp in self._handle_mail_object: {0}".format(e)
self._debug_print(message)
return phantom.APP_ERROR, message, []
results = [{"container": self._container, "artifacts": self._artifacts, "files": self._attachments, "temp_directory": tmp_dir}]
return ret_val, "Email Parsed", results
def process_email(self, base_connector, rfc822_email, email_id, config, epoch, container_id=None, email_headers=None, attachments_data=None):
self._base_connector = base_connector
self._config = config
if email_headers:
for curr_header in email_headers:
self._headers_from_ews.append(CaseInsensitiveDict(curr_header))
if (config[PROC_EMAIL_JSON_EXTRACT_ATTACHMENTS]) and (attachments_data is not None):
self._attachments_from_ews = attachments_data
try:
self._set_email_id_contains(email_id)
except Exception:
pass
ret_val, message, results = self._int_process_email(rfc822_email, email_id, epoch)
if not ret_val:
self._del_tmp_dirs()
return phantom.APP_ERROR, message
try:
self._parse_results(results, container_id)
except Exception:
self._del_tmp_dirs()
raise
return phantom.APP_SUCCESS, "Email Processed"
def _save_ingested(self, container, using_dummy):
if using_dummy:
cid = container["id"]
artifacts = container["artifacts"]
for artifact in artifacts:
artifact["container_id"] = cid
ret_val, message, ids = self._base_connector.save_artifacts(artifacts)
self._base_connector.debug_print("save_artifacts returns, value: {0}, reason: {1}".format(ret_val, message))