-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathjava_triage.py
More file actions
8060 lines (7431 loc) · 334 KB
/
java_triage.py
File metadata and controls
8060 lines (7431 loc) · 334 KB
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
#!/usr/bin/env python3
import argparse
import base64
import bisect
import hashlib
import json
import math
import os
import re
import shutil
import subprocess
import sys
import tempfile
import time
import zipfile
from datetime import datetime
from dataclasses import dataclass
from pathlib import Path
from typing import Any, Iterable, List, Optional
from urllib import error, request
from urllib.parse import urlparse
try:
from rich.console import Console
from rich.table import Table
from rich.rule import Rule
from rich.panel import Panel
from rich.text import Text
from rich import box
from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn, MofNCompleteColumn, TimeElapsedColumn
RICH_AVAILABLE = True
except Exception:
RICH_AVAILABLE = False
BANNER = r"""
██ █████ ██ ██ █████ ████████ ██████ ██ █████ ██████ ███████
██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██
██ ███████ ██ ██ ███████ ██ ██████ ██ ███████ ██ ███ █████
██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ██
█████ ██ ██ ████ ██ ██ ██ ██ ██ ██ ██ ██ ██████ ███████
https://github.com/cev-api/Java-Triage
"""
LOAD_CALL_RE = re.compile(
r"(?:\b\w+\.)?load\(\s*new\s+int\[\]\s*\{(?P<d1>.*?)\}\s*,\s*new\s+int\[\]\s*\{(?P<d2>.*?)\}\s*,\s*(?P<k1>\d+)\s*,\s*(?P<k2>\d+)\s*\)",
re.DOTALL,
)
# Match standard Java string literals and avoid crossing line boundaries.
STRING_LITERAL_RE = re.compile(r'"((?:\\.|[^"\\\r\n]){16,})"')
STRING_ANY_LITERAL_RE = re.compile(r'"((?:\\.|[^"\\\r\n]){4,})"')
STRING_SHORT_LITERAL_RE = re.compile(r'"((?:\\.|[^"\\\r\n]){1,64})"')
SPLIT_STRING_ARRAY_RE = re.compile(
r"String\[\]\s+(?P<name>[A-Za-z_$][\w$]*)\s*=\s*new\s+String\[\]\s*\{(?P<body>.*?)\};",
re.DOTALL,
)
STRING_DECRYPT_CALL_RE = re.compile(
r"(?P<call>(?:\b[\w$.]*StringDecrypt\s*\.\s*)?decrypt\s*\(\s*new\s+byte\s*\[\s*\]\s*\{(?P<bytes>.*?)\}\s*\))",
re.DOTALL,
)
NEW_BYTE_ARRAY_LITERAL_RE = re.compile(r"new\s+byte\s*\[\s*\]\s*\{(?P<body>.*?)\}", re.DOTALL)
NEW_CHAR_ARRAY_LITERAL_RE = re.compile(r"new\s+char\s*\[\s*\]\s*\{(?P<body>.*?)\}", re.DOTALL)
STRINGBUILDER_REVERSE_RE = re.compile(
r'new\s+StringBuilder\(\s*"(?P<lit>(?:\\.|[^"\\\r\n]){4,})"\s*\)\.reverse\(\)\.toString\(\)',
re.DOTALL,
)
JAVA_BYTE_TOKEN_RE = re.compile(r"(?:\(\s*byte\s*\)\s*)?(-?\d+)")
JAVA_CHAR_TOKEN_RE = re.compile(r"(?:\(\s*char\s*\)\s*)?(-?\d+)")
METHOD_RE = re.compile(
r"^\s*(?:public|private|protected|static|final|synchronized|native|abstract|strictfp|default|\s)+"
r"(?:<[\w\s,? extends super]+>\s*)?"
r"[\w$\[\]<>.,?\s]+\s+([A-Za-z_$][\w$]*)\s*\([^;{}]*\)\s*(?:throws\s+[^{]+)?\{\s*$"
)
URL_RE = re.compile(r"^https?://", re.IGNORECASE)
HEX_ADDR_RE = re.compile(r"^0x[a-fA-F0-9]{8,}$")
ETH_SELECTOR_RE = re.compile(r"^0x[a-fA-F0-9]{8}$")
BASE64_RE = re.compile(r"^[A-Za-z0-9+/=]{80,}$")
BASE32_RE = re.compile(r"^[A-Z2-7=]{16,}$")
HEX_BLOB_RE = re.compile(r"^(?:[A-Fa-f0-9]{2}){8,}$")
RESOURCE_STREAM_RE = re.compile(r'getResourceAsStream\(\s*"([^"]+)"\s*\)')
CREATE_TEMP_RE = re.compile(r'createTempFile\(\s*"([^"]*)"\s*,\s*([^)]+)\)')
COMMAND_LITERAL_RE = re.compile(
r"(?:\bcmd\.exe\b|\bpowershell(?:\.exe)?\b|\brundll32\b|\bregsvr32\b|\bmshta\b|\bwmic\b|\bcertutil\b|\bcmstp\b|/c\b|-enc\b)",
re.IGNORECASE,
)
WINDOWS_PATH_RE = re.compile(r"^[A-Za-z]:\\")
SUSPICIOUS_STRING_KEYWORDS = (
"webhook",
"discord",
"dqw4w9wgxcq",
"telegram",
"api.telegram.org",
"proguard",
"allatori",
"stringer",
"zelix",
"dasho",
"api_key",
"authorization",
"bearer ",
"token",
"exfil",
"pastebin",
"ngrok",
"defender",
"uac",
"elevate",
"download",
)
DISCORD_WEBHOOK_RE = re.compile(
r"^https?://(?:ptb\.|canary\.)?discord(?:app)?\.com/api/webhooks/(?P<id>\d{17,20})/(?P<token>[A-Za-z0-9._-]{20,})$",
re.IGNORECASE,
)
DISCORD_BOT_TOKEN_RE = re.compile(
r"\b(?:mfa\.[A-Za-z0-9_-]{20,}|[A-Za-z0-9_-]{23,28}\.[A-Za-z0-9_-]{6,8}\.[A-Za-z0-9_-]{20,})\b"
)
DISCORD_ENCRYPTED_TOKEN_MARKER_RE = re.compile(r"dQw4w9WgXcQ:(?P<payload>[A-Za-z0-9+/=]+)")
TELEGRAM_BOT_TOKEN_RE = re.compile(r"\b\d{8,12}:[A-Za-z0-9_-]{30,60}\b")
GENERIC_WEBHOOK_URL_RE = re.compile(
r"^https?://[^\s\"'<>]+/(?:api/)?(?:v\d+/)?(?:webhook|webhooks|hooks?)/[^\s\"'<>]+$",
re.IGNORECASE,
)
DISCORD_SNOWFLAKE_RE = re.compile(r"^\d{17,20}$")
DISCORD_SNOWFLAKE_ANY_RE = re.compile(r"\b\d{17,20}\b")
DISCORD_ID_CONTEXT_RE = re.compile(
r"(?:\bguild(?:_id)?\b|\bserver(?:_id)?\b|\bchannel(?:_id)?\b|\buser(?:_id)?\b|\brole(?:_id)?\b|\bapplication(?:_id)?\b|\bdiscord\b)",
re.IGNORECASE,
)
HTTP_HOST_RE = re.compile(r'https?://([^/:\s"\'<>]+)', re.IGNORECASE)
ASSESSMENT_PREFIX = "assessment_"
BEHAVIOR_SEVERITY_ORDER = {"critical": 4, "high": 3, "medium": 2, "low": 1, "info": 0}
BEHAVIOR_SEVERITY_MAP = {
"assessment_suspicious_possible_credential_exfiltration": "high",
"assessment_suspicious_remote_mod_dropper": "high",
"assessment_suspicious_embedded_mod_dropper": "high",
"assessment_suspicious_discord_token_stealer": "high",
"assessment_suspicious_multi_credential_infostealer": "critical",
"assessment_needs_review_remote_mod_downloader": "medium",
"assessment_needs_review_access_token_read_without_destination": "medium",
"assessment_benign_fake_player_clone": "low",
"assessment_benign_self_name_filtering": "low",
"assessment_benign_session_override_for_alt_switching": "low",
"assessment_benign_token_use_local_profilekey_setup": "low",
"assessment_benign_token_getter_passthrough": "low",
"assessment_benign_token_use_minecraft_auth_chain": "low",
"uac_bypass_cmstp": "high",
"defender_tampering": "high",
"command_execution_capability": "high",
"credential_exfiltration_post": "high",
"credential_handoff_to_dynamic_stage": "critical",
"staged_remote_jar_execution": "critical",
"blockchain_backed_c2_bootstrap": "high",
"possible_access_token_exfiltration": "high",
"remote_urlclassloader_usage": "high",
"possible_minecraft_session_file_exfiltration": "high",
"possible_minecraft_identity_exfiltration": "high",
"minecraft_mod_folder_remote_dropper": "high",
"minecraft_mod_folder_embedded_payload_dropper": "high",
"embedded_resource_encoded_archive_dropper": "high",
"discord_leveldb_token_theft": "high",
"discord_token_validation_api": "high",
"discord_token_exfiltration_bundle": "high",
"browser_password_database_theft": "high",
"browser_cookie_database_theft": "high",
"browser_history_database_collection": "medium",
"screenshot_capture_collection": "high",
"chromium_masterkey_decryption_chain": "high",
"runtime_sqlite_driver_download_and_load": "high",
"credential_exfiltration_endpoint": "high",
"decompiler_failure_or_heavy_obfuscation": "high",
"class_constant_pool_only_scan": "medium",
"extreme_archive_structure_obfuscation": "high",
"http_urlconnection_binary_download": "medium",
"obfuscated_url_reconstruction": "medium",
"dropper_elevation_helper": "high",
"second_stage_jar_unpack": "high",
"embedded_native_payload_loader": "high",
"sandbox_escape_primitive_usage": "high",
"dynamic_urlclassloader_usage": "medium",
"obfuscator_or_packer_marker": "medium",
"binary_payload_download": "medium",
"dynamic_class_execution": "medium",
"stealth_relaunch": "medium",
"jnic_obfuscator_native_stub_usage": "medium",
"windows_arch_payload_slicing": "medium",
"native_code_execution_capability": "medium",
"minecraft_session_file_access": "medium",
"custom_decompression_runtime_internals": "medium",
"windows_amd64_payload_range": "info",
"windows_aarch64_payload_range": "info",
"telemetry_or_beaconing": "low",
"minecraft_gameprofile_access": "low",
"minecraft_session_access": "low",
"minecraft_username_access": "low",
"minecraft_uuid_access": "low",
"minecraft_access_token_access": "medium",
"minecraft_session_id_access": "medium",
"token_field_getter_passthrough": "low",
"profile_use_fake_player_clone": "low",
"profile_use_self_name_filtering": "low",
"session_profile_override": "medium",
"username_or_session_switching": "medium",
"mixed_token_destinations_review": "medium",
"token_sent_to_minecraft_auth_chain": "low",
"token_use_profile_key_or_user_api_setup": "low",
"remote_config_rpc_with_signature": "medium",
"obfuscated_short_classname_cluster": "low",
"proof_token_source_to_network_sink": "high",
"proof_raw_token_logging": "high",
"proof_reachable_command_token_disclosure_chain": "critical",
"exposed_local_websocket_command_bridge": "high",
"capability_token_access": "medium",
"audio_capture_capability": "high",
"audio_playback_capability": "low",
}
MINECRAFT_AUTH_HOSTS = {
"login.live.com",
"auth.xboxlive.com",
"user.auth.xboxlive.com",
"xsts.auth.xboxlive.com",
"api.minecraftservices.com",
}
VENDOR_HOST_ALLOWLIST = {
"login.live.com",
"login.microsoftonline.com",
"device.auth.xboxlive.com",
"user.auth.xboxlive.com",
"xsts.auth.xboxlive.com",
"api.minecraftservices.com",
"pc.realms.minecraft.net",
"pocket.realms.minecraft.net",
"minecraft.playfabapi.com",
"api.keygen.sh",
"discord.com",
"discordapp.com",
"github.com",
"api.github.com",
}
KNOWN_LIBRARY_PREFIXES = {
"raphimc_minecraftauth": ["net/raphimc/minecraftauth/"],
"discord_rpc": ["net/arikia/dev/drpc/"],
"lenni_httpclient": ["net/lenni0451/commons/httpclient/"],
"lenni_gson": ["net/lenni0451/commons/gson/"],
"gson": ["com/google/gson/"],
"java_websocket": ["org/java_websocket/"],
"slf4j": ["org/slf4j/"],
"fabric": ["net/fabricmc/", "fabric/"],
"org_json": ["org/json/"],
"jna": ["com/sun/jna/"],
}
def _is_known_library_relpath(rel_path: str) -> bool:
rel_low = str(rel_path or "").replace("\\", "/").lower().lstrip("./")
for prefixes in KNOWN_LIBRARY_PREFIXES.values():
if any(rel_low.startswith(prefix.lower()) for prefix in prefixes):
return True
return False
RAW_STRING_PATTERNS = [
("erawaggin", "Reversed 'niggaware' string", 50),
("erawoobmab", "Reversed 'bambooware' string", 50),
("DirectPlayerDetector", "Niggaware thread name", 25),
("performance-tweaks", "Niggaware mod ID", 25),
("Add-MpPreference", "Defender exclusion command", 30),
("dev.github.Main", "Silentnet stage2 entry", 30),
("Mod init state: M", "Weedhack debug string", 30),
("Resource state: S", "Weedhack debug string", 30),
("method_1674", "MC accessToken accessor", 20),
("method_1675", "MC sessionId accessor", 20),
("method_38740", "MC clientId accessor", 15),
("method_38741", "MC xuid accessor", 15),
("method_35718", "MC accountType accessor", 15),
("method_1676", "MC username accessor", 20),
("method_1673", "MC UUID accessor", 20),
("method_44717", "MC UUID accessor", 20),
("func_110432_I", "Legacy MCP getSession accessor", 20),
("func_111286_b", "Legacy MCP getSessionID accessor", 20),
("func_148254_d", "Legacy MCP raw token accessor", 20),
("field_1983", "MC accessToken field", 20),
("field_148258_c", "Legacy MCP token field", 20),
("field_34961", "MC clientId field", 15),
("field_34960", "MC xuid field", 15),
("field_1984", "MC accountType field", 15),
("field_71449_j", "Legacy MCP Minecraft.session field", 15),
("field_1726", "Intermediary MinecraftClient.session field", 15),
("net.minecraft.client.User", "Mojmap/NeoForge User class", 15),
("net.minecraft.class_320", "Intermediary Session class", 15),
("Lnet/minecraft/class_310;method_1551()Lnet/minecraft/class_310;", "Intermediary MinecraftClient.getInstance descriptor", 20),
("Lnet/minecraft/class_310;method_1548()Lnet/minecraft/class_320;", "Intermediary MinecraftClient.getSession descriptor", 20),
("Lnet/minecraft/class_320;method_1674()Ljava/lang/String;", "Intermediary Session.getAccessToken descriptor", 20),
("Lnet/minecraft/class_320;method_1675()Ljava/lang/String;", "Intermediary Session.getSessionId descriptor", 20),
("Lnet/minecraft/class_320;field_1983:Ljava/lang/String;", "Intermediary Session.accessToken field descriptor", 20),
("Lnet/minecraft/client/session/Session;accessToken:Ljava/lang/String;", "Yarn Session.accessToken field descriptor", 20),
("Lnet/minecraft/client/util/Session;accessToken:Ljava/lang/String;", "Yarn legacy Session.accessToken field descriptor", 20),
("Lnet/minecraft/client/User;accessToken:Ljava/lang/String;", "Mojmap User.accessToken field descriptor", 20),
("Lnet/minecraft/util/Session;field_148258_c:Ljava/lang/String;", "MCP Session.token field descriptor", 20),
("eth_call", "Ethereum RPC call", 15),
("0x70a08231", "Ethereum balanceOf selector", 15),
("Wscript.Shell", "Windows Script Host", 20),
("powershell", "PowerShell execution", 15),
("RuntimeBroker", "Process masquerading as RuntimeBroker", 20),
]
AUTO_DECRYPT_TRIGGER_MIN_CALLS = 1
AUTO_DECRYPT_TRIGGER_MIN_FILE_RATIO = 0.0
AUTO_DECRYPT_TRIGGER_MIN_FILES_WITH_CALLS = 1
MAJOR_ENCRYPTED_MIN_CALLS = 200
MAJOR_ENCRYPTED_MIN_FILE_RATIO = 0.20
MAJOR_ENCRYPTED_MIN_FILES_WITH_CALLS = 5
OPENAI_CHAT_COMPLETIONS_URL = "https://api.openai.com/v1/chat/completions"
DEEPSEEK_CHAT_COMPLETIONS_URL = "https://api.deepseek.com/v1/chat/completions"
RATTERSCANNER_HASH_URL = "https://api.ratterscanner.com/hash/"
JLAB_STATIC_SCAN_URL = "https://jlab.threat.rip/api/public/static-scan"
JLAB_MAX_UPLOAD_BYTES = 50 * 1024 * 1024
OPENAI_EXEC_SUMMARY_INSTRUCTION = (
"Parse the JSON and create an executive summary of the result detailing the flow of the malware "
"or application (if clean) and its capabilities, risks, goal. Keep it technical but understandable "
"for both layman and professional. Max 500 words. Output must be plain text optimized for terminal "
"display. Do NOT use markdown headings, bold/italic markers, tables, code fences, horizontal rules, "
"or backticks. Use short section labels and simple bullet lines prefixed with '- '. Prioritize "
"confirmed_behavior proof chains over generic suspicious indicators. Explicitly include caveats from "
"contradiction_notes and avoid overstating automatic exfiltration when only exposure is proven."
)
def _is_sha256_hex(value: str) -> bool:
return bool(re.fullmatch(r"[a-fA-F0-9]{64}", (value or "").strip()))
def collect_ratterscanner_hashes(
target_metadata: dict,
artifacts: List[Any],
stage2_analysis: dict | None = None,
scan_root: Path | None = None,
) -> List[str]:
out: List[str] = []
basic = (target_metadata or {}).get("basic_properties", {}) or {}
s = str(basic.get("sha256", "") or "").strip().lower()
if _is_sha256_hex(s):
out.append(s)
for a in artifacts or []:
h = str(getattr(a, "sha256", "") or "").strip().lower()
if _is_sha256_hex(h):
out.append(h)
s2 = stage2_analysis or {}
h2 = str(s2.get("download_sha256", "") or "").strip().lower()
if _is_sha256_hex(h2):
out.append(h2)
if scan_root is not None:
marker = scan_root / ".java_triage_source_jar_sha256.txt"
if marker.is_file():
try:
m = marker.read_text(encoding="utf-8", errors="replace").strip().lower()
if _is_sha256_hex(m):
out.append(m)
except Exception:
pass
dedup: List[str] = []
seen: set[str] = set()
for h in out:
if h in seen:
continue
seen.add(h)
dedup.append(h)
return dedup[:50]
def lookup_ratterscanner(hashes: List[str], timeout: int = 20) -> dict:
valid = [h.strip().lower() for h in hashes if _is_sha256_hex(h)]
out = {"attempted": False, "error": "", "results": []}
if not valid:
return out
out["attempted"] = True
try:
url = RATTERSCANNER_HASH_URL + ",".join(valid)
req = request.Request(url, method="GET", headers={"User-Agent": "java-triage/1.0"})
with request.urlopen(req, timeout=timeout) as resp:
data = json.loads(resp.read().decode("utf-8", errors="replace"))
if isinstance(data, dict) and isinstance(data.get("results"), list):
out["results"] = data.get("results") or []
return out
if isinstance(data, dict) and data.get("error"):
out["error"] = str(data.get("error"))
return out
out["error"] = "invalid response format"
return out
except Exception as exc:
out["error"] = _friendly_network_error(exc)
return out
def _parse_int_header(headers: Any, name: str) -> int | None:
if headers is None:
return None
try:
raw = str(headers.get(name, "") or "").strip()
except Exception:
return None
if not raw:
return None
try:
return int(raw)
except Exception:
return None
def lookup_jlab_static_scan(upload_path: Path, timeout: int = 45) -> dict:
out = {
"attempted": False,
"error": "",
"status_code": 0,
"upload_file": "",
"upload_size": 0,
"file_name": "",
"file_size": 0,
"total_signatures": 0,
"matched_signatures": 0,
"signatures": [],
"retry_after": None,
"rate_limit_limit": None,
"rate_limit_remaining": None,
}
if not upload_path.is_file():
out["error"] = "JLab static scan skipped: upload file not found"
return out
ext = upload_path.suffix.lower()
if ext not in {".jar", ".zip"}:
out["error"] = "JLab static scan skipped: upload must be .jar or .zip"
return out
try:
size = int(upload_path.stat().st_size)
except Exception:
out["error"] = "JLab static scan skipped: failed to read upload file size"
return out
if size <= 0:
out["error"] = "JLab static scan skipped: upload file is empty"
return out
if size > JLAB_MAX_UPLOAD_BYTES:
out["error"] = f"JLab static scan skipped: file exceeds 50 MB ({size} bytes)"
return out
out["attempted"] = True
out["upload_file"] = upload_path.name
out["upload_size"] = size
boundary = f"----JavaTriageBoundary{int(time.time() * 1000)}"
mime = "application/java-archive" if ext == ".jar" else "application/zip"
try:
file_bytes = upload_path.read_bytes()
body_prefix = (
f"--{boundary}\r\n"
f'Content-Disposition: form-data; name="file"; filename="{upload_path.name}"\r\n'
f"Content-Type: {mime}\r\n\r\n"
).encode("utf-8")
body_suffix = f"\r\n--{boundary}--\r\n".encode("utf-8")
payload = body_prefix + file_bytes + body_suffix
req = request.Request(
JLAB_STATIC_SCAN_URL,
method="POST",
data=payload,
headers={
"User-Agent": "java-triage/1.0",
"Content-Type": f"multipart/form-data; boundary={boundary}",
"Content-Length": str(len(payload)),
},
)
with request.urlopen(req, timeout=timeout) as resp:
out["status_code"] = int(getattr(resp, "status", 200) or 200)
out["retry_after"] = _parse_int_header(resp.headers, "Retry-After")
out["rate_limit_limit"] = _parse_int_header(resp.headers, "X-RateLimit-Limit")
out["rate_limit_remaining"] = _parse_int_header(resp.headers, "X-RateLimit-Remaining")
raw = resp.read().decode("utf-8", errors="replace")
data = json.loads(raw) if raw.strip() else {}
if isinstance(data, dict) and bool(data.get("success")):
out["file_name"] = str(data.get("fileName", "") or "")
out["file_size"] = int(data.get("fileSize", 0) or 0)
out["total_signatures"] = int(data.get("totalSignatures", 0) or 0)
out["matched_signatures"] = int(data.get("matchedSignatures", 0) or 0)
sigs = data.get("signatures", [])
out["signatures"] = sigs if isinstance(sigs, list) else []
return out
if isinstance(data, dict) and data.get("error"):
out["error"] = str(data.get("error", "") or "unknown API error")
return out
out["error"] = "invalid response format"
return out
except error.HTTPError as exc:
out["status_code"] = int(getattr(exc, "code", 0) or 0)
out["retry_after"] = _parse_int_header(exc.headers, "Retry-After")
out["rate_limit_limit"] = _parse_int_header(exc.headers, "X-RateLimit-Limit")
out["rate_limit_remaining"] = _parse_int_header(exc.headers, "X-RateLimit-Remaining")
body = ""
try:
body = exc.read().decode("utf-8", errors="replace")
except Exception:
body = ""
message = ""
if body.strip():
try:
parsed = json.loads(body)
if isinstance(parsed, dict):
message = str(parsed.get("error", "") or "")
if out["retry_after"] is None:
out["retry_after"] = _parse_int_header(parsed, "retryAfter")
if out["rate_limit_limit"] is None:
out["rate_limit_limit"] = _parse_int_header(parsed, "limit")
if out["rate_limit_remaining"] is None:
out["rate_limit_remaining"] = _parse_int_header(parsed, "remaining")
except Exception:
message = body.strip()
if not message:
message = str(exc)
if exc.code == 429 and out["retry_after"]:
out["error"] = f"Rate limit exceeded. Try again in {out['retry_after']}s."
elif exc.code == 413:
out["error"] = "File exceeds 50 MB upload limit"
else:
out["error"] = message
return out
except Exception as exc:
out["error"] = _friendly_network_error(exc)
return out
@dataclass
class Finding:
file: str
line: int
function: str
decoded: str
category: str
note: str = ""
@dataclass
class BehaviorFinding:
file: str
line: int
behavior: str
evidence: str
@dataclass
class ArtifactFinding:
path: str
filename: str
size: int
sha256: str
artifact_type: str
evidence: str
@dataclass
class DecryptProfile:
key_arrays: List[List[int]]
xor_consts: List[int]
add_consts: List[int]
sub_consts: List[int]
def parse_int_list(raw: str) -> List[int]:
parts = [p.strip() for p in raw.split(",") if p.strip()]
return [int(p) for p in parts]
def _to_signed_byte(n: int) -> int:
n = int(n)
n &= 0xFF
return n - 256 if n >= 128 else n
def parse_java_byte_list(raw: str) -> List[int]:
vals: List[int] = []
for m in JAVA_BYTE_TOKEN_RE.finditer(raw):
vals.append(_to_signed_byte(int(m.group(1))))
return vals
def _decode_java_string_literal_fragment(raw: str) -> str:
try:
return bytes(raw, "utf-8").decode("unicode_escape")
except Exception:
return raw
def _reconstruct_split_string_arrays(text: str) -> List[tuple[str, str, int, int]]:
out: List[tuple[str, str, int, int]] = []
for m in SPLIT_STRING_ARRAY_RE.finditer(text):
body = m.group("body")
parts_raw = STRING_SHORT_LITERAL_RE.findall(body)
if len(parts_raw) < 8:
continue
parts = [_decode_java_string_literal_fragment(p) for p in parts_raw]
joined = "".join(parts).strip()
if len(joined) < 12:
continue
line = text.count("\n", 0, m.start()) + 1
out.append((m.group("name"), joined, line, len(parts)))
return out
def _extract_printable_byte_array_strings(
text: str,
max_arrays: int = 120,
max_bytes: int = 4096,
) -> List[tuple[str, int, int]]:
out: List[tuple[str, int, int]] = []
seen = set()
for idx, m in enumerate(NEW_BYTE_ARRAY_LITERAL_RE.finditer(text)):
if idx >= max_arrays:
break
vals = parse_java_byte_list(m.group("body"))
if not vals or len(vals) > max_bytes:
continue
raw = bytes((v + 256) % 256 for v in vals)
if not _mostly_printable(raw):
continue
decoded = _to_printable(raw).replace("\x00", "").strip()
if len(decoded) < 4 or decoded in seen:
continue
seen.add(decoded)
line = text.count("\n", 0, m.start()) + 1
out.append((decoded, line, len(vals)))
return out
def _extract_printable_char_array_strings(
text: str,
max_arrays: int = 120,
min_len: int = 4,
max_len: int = 4096,
) -> List[tuple[str, int, int]]:
out: List[tuple[str, int, int]] = []
seen = set()
for idx, m in enumerate(NEW_CHAR_ARRAY_LITERAL_RE.finditer(text)):
if idx >= max_arrays:
break
vals = []
for tm in JAVA_CHAR_TOKEN_RE.finditer(m.group("body")):
try:
vals.append(int(tm.group(1)))
except Exception:
continue
if not vals or len(vals) < min_len or len(vals) > max_len:
continue
chars = []
printable = 0
for v in vals:
v &= 0xFFFF
try:
ch = chr(v)
except Exception:
ch = ""
chars.append(ch)
if ch and (ch == "\t" or ch == "\n" or ch == "\r" or 32 <= ord(ch) <= 126):
printable += 1
if printable / max(1, len(chars)) < 0.85:
continue
decoded = "".join(chars).replace("\x00", "").strip()
if len(decoded) < min_len or decoded in seen:
continue
seen.add(decoded)
line = text.count("\n", 0, m.start()) + 1
out.append((decoded, line, len(vals)))
return out
def _extract_reversed_stringbuilder_literals(text: str, max_hits: int = 100) -> List[tuple[str, int, int]]:
out: List[tuple[str, int, int]] = []
seen = set()
for idx, m in enumerate(STRINGBUILDER_REVERSE_RE.finditer(text)):
if idx >= max_hits:
break
raw = _decode_java_string_literal_fragment(m.group("lit"))
decoded = raw[::-1].strip()
if len(decoded) < 4 or decoded in seen:
continue
seen.add(decoded)
line = text.count("\n", 0, m.start()) + 1
out.append((decoded, line, len(raw)))
return out
def _java_string_escape(s: str) -> str:
out = []
for ch in s:
code = ord(ch)
if ch == "\\":
out.append("\\\\")
elif ch == '"':
out.append('\\"')
elif ch == "\n":
out.append("\\n")
elif ch == "\r":
out.append("\\r")
elif ch == "\t":
out.append("\\t")
elif 32 <= code <= 126:
out.append(ch)
else:
out.append(f"\\u{code:04x}")
return "".join(out)
def _extract_candidate_consts(text: str, op: str) -> List[int]:
vals = set()
pattern = re.compile(rf"\{re.escape(op)}\s*(?:\(\s*byte\s*\)\s*)?(-?\d+)")
for m in pattern.finditer(text):
v = int(m.group(1))
if -255 <= v <= 255:
vals.add(v & 0xFF)
return sorted(vals)
def build_decrypt_profile(root: Path) -> Optional[DecryptProfile]:
keys: List[List[int]] = []
xor_consts: List[int] = []
add_consts: List[int] = []
sub_consts: List[int] = []
decrypt_files = [p for p in root.rglob("*StringDecrypt*.java") if p.is_file()]
if not decrypt_files:
return None
for p in decrypt_files:
text = p.read_text(encoding="utf-8", errors="replace")
for m in NEW_BYTE_ARRAY_LITERAL_RE.finditer(text):
arr = parse_java_byte_list(m.group("body"))
if 2 <= len(arr) <= 64:
keys.append(arr)
xor_consts.extend(_extract_candidate_consts(text, "^"))
add_consts.extend(_extract_candidate_consts(text, "+"))
sub_consts.extend(_extract_candidate_consts(text, "-"))
key_unique = []
seen_keys = set()
for k in keys:
t = tuple(k)
if t in seen_keys:
continue
seen_keys.add(t)
key_unique.append(k)
xor_unique = sorted(set(xor_consts))
add_unique = sorted(set(add_consts))
sub_unique = sorted(set(sub_consts))
return DecryptProfile(
key_arrays=key_unique,
xor_consts=xor_unique,
add_consts=add_unique,
sub_consts=sub_unique,
)
def _score_plaintext(s: str) -> float:
if not s:
return 0.0
printable = sum(1 for ch in s if ch == "\n" or ch == "\r" or ch == "\t" or 32 <= ord(ch) <= 126)
ratio = printable / len(s)
alpha = sum(1 for ch in s if ch.isalpha()) / len(s)
common = ["http", "post", "get", "authorization", "content-type", "json", "token", "hwid", "user-agent", "accept"]
low = s.lower()
bonus = 0.0
for tok in common:
if tok in low:
bonus += 0.2
return ratio * 1.6 + alpha * 0.4 + bonus
def _looks_meaningful_text(s: str) -> bool:
if not s:
return False
ascii_printable = sum(1 for ch in s if ch in "\t\r\n" or 32 <= ord(ch) <= 126)
ratio = ascii_printable / len(s)
if ratio < 0.95:
return False
stripped = s.strip()
if not stripped:
return False
if len(stripped) <= 3:
allowed_short = {"GET", "POST", "PUT", "PATCH", "DELETE", "HEAD", "OK", "ID", "API"}
return stripped.upper() in allowed_short
letters = sum(1 for ch in stripped if ch.isalpha())
digits = sum(1 for ch in stripped if ch.isdigit())
symbols = len(stripped) - letters - digits - sum(1 for ch in stripped if ch.isspace())
if letters == 0:
return False
if letters < 2 and len(stripped) >= 5:
return False
if symbols > max(4, len(stripped) // 2):
return False
return True
def _bytes_to_text(raw: bytes) -> str:
try:
return raw.decode("utf-8")
except Exception:
return raw.decode("latin-1", errors="replace")
def _decode_len_seed_xor_stream(raw: bytes, seed_magic: int, mul_const: int) -> bytes:
key = (len(raw) ^ seed_magic) & 0xFF
out = bytearray(len(raw))
for i, b in enumerate(raw):
key = ((key * mul_const) >> 16) & 0xFF
out[i] = (b ^ key ^ (i >> 1)) & 0xFF
key ^= i
return bytes(out)
def _candidate_decodes_for_byte_array(vals: List[int], profile: Optional[DecryptProfile]) -> List[tuple[str, str]]:
if not vals:
return []
raw = bytes(v & 0xFF for v in vals)
out: List[tuple[str, str]] = []
seen = set()
def add_candidate(b: bytes, why: str) -> None:
t = _bytes_to_text(b)
key = (t, why)
if key in seen:
return
seen.add(key)
out.append((t, why))
add_candidate(raw, "byte_array_raw")
# Deterministic length-seeded XOR stream family (common in commodity Java obfuscators).
add_candidate(
_decode_len_seed_xor_stream(raw, seed_magic=1313161813, mul_const=73244475),
"byte_array_len_seed_xor_stream magic=1313161813 mul=73244475",
)
for key in range(1, 256):
dec = bytes((b ^ key) & 0xFF for b in raw)
add_candidate(dec, f"byte_array_xor_single key=0x{key:02X}")
if profile:
for c in profile.xor_consts:
dec = bytes((b ^ c) & 0xFF for b in raw)
add_candidate(dec, f"byte_array_xor_const key=0x{c:02X}")
for c in profile.add_consts:
dec = bytes((b + c) & 0xFF for b in raw)
add_candidate(dec, f"byte_array_add_const n={c}")
for c in profile.sub_consts:
dec = bytes((b - c) & 0xFF for b in raw)
add_candidate(dec, f"byte_array_sub_const n={c}")
for arr in profile.key_arrays:
if not arr:
continue
dec = bytes(((b ^ (arr[i % len(arr)] & 0xFF)) & 0xFF) for i, b in enumerate(raw))
add_candidate(dec, f"byte_array_xor_keyarray len={len(arr)}")
return out
def decode_stringdecrypt_bytes(vals: List[int], profile: Optional[DecryptProfile]) -> tuple[str, str]:
best = ""
best_note = ""
best_score = 0.0
for text, note in _candidate_decodes_for_byte_array(vals, profile):
score = _score_plaintext(text)
if score > best_score:
best_score = score
best = text
best_note = note
if best and best_score >= 1.50 and _looks_meaningful_text(best):
return best, best_note
return "", ""
def decode_stringdecrypt_bytes_fallback(vals: List[int], profile: Optional[DecryptProfile]) -> tuple[str, str]:
best = ""
best_note = ""
best_score = 0.0
for text, note in _candidate_decodes_for_byte_array(vals, profile):
score = _score_plaintext(text)
if score > best_score:
best_score = score
best = text
best_note = note
if not best:
return "", ""
# Lower-confidence fallback for standard scan mode to avoid dropping all encrypted literals.
ascii_printable = sum(1 for ch in best if ch in "\t\r\n" or 32 <= ord(ch) <= 126)
ratio = ascii_printable / len(best) if best else 0.0
if ratio < 0.75:
return "", ""
if "\x00" in best:
return "", ""
if best_score < 1.10:
return "", ""
return best, f"{best_note} forced_low_confidence"
def decode_stringdecrypt_bytes_force(vals: List[int], profile: Optional[DecryptProfile]) -> tuple[str, str]:
best = ""
best_note = ""
best_score = -1.0
for text, note in _candidate_decodes_for_byte_array(vals, profile):
score = _score_plaintext(text)
if score > best_score:
best_score = score
best = text
best_note = note
if not best:
return "", ""
if "\x00" in best:
best = best.replace("\x00", "")
if not best:
return "", ""
return best, f"{best_note} forced_any"
def decode_obf(d1: List[int], d2: List[int], k1: int, k2: int) -> str:
length = len(d1) + len(d2)
data = [0] * length
for i, v in enumerate(d1):
data[i * 2] = v
for i, v in enumerate(d2):
data[i * 2 + 1] = v
sbox = [0] * 256
for i in range(256):
sbox[i] = (i * 53 + 97) % 256
inv_sbox = [0] * 256
for i in range(256):
inv_sbox[sbox[i]] = i
state = k2
out = []
for idx, value in enumerate(data):
state = (state * 37 + idx * 13) % 256
mask = (k2 + state + idx * 11) % 256
if idx > 0:
value ^= data[idx - 1]
else:
value ^= k2
shift = (idx * 5 + k1) % 8
rotated = ((value >> shift) | (value << (8 - shift))) & 0xFF
substituted = inv_sbox[rotated]
ch = chr((substituted ^ mask ^ k1) & 0xFFFF)
out.append(ch)
return "".join(out)
def build_line_starts(text: str) -> List[int]:
starts = [0]
for i, ch in enumerate(text):
if ch == "\n":
starts.append(i + 1)
return starts
def offset_to_line(line_starts: List[int], offset: int) -> int:
return bisect.bisect_right(line_starts, offset)
def find_method_declarations(lines: List[str]) -> List[tuple[int, str]]:
decls = []
for idx, line in enumerate(lines, start=1):
m = METHOD_RE.match(line)
if not m:
continue
name = m.group(1)
if name in {"if", "for", "while", "switch", "catch", "return", "new"}:
continue
decls.append((idx, name))
return decls
def nearest_method(decls: List[tuple[int, str]], line: int) -> str:
method = "<unknown>"
for decl_line, decl_name in decls:
if decl_line <= line:
method = decl_name
else:
break
return method
def classify(decoded: str) -> str:
d = decoded.strip()
low = d.lower()
discord_kind, _ = detect_discord_indicator(d)
if discord_kind:
if discord_kind == "discord_encrypted_token_marker":
return "credential_or_identity_field"
return "discord_indicator"
endpoint_kind, _ = detect_external_endpoint_indicator(d)