heitt 0.4.5 → 0.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/bin/heitt +96 -58
- data/lib/heitt/analyzer.rb +153 -0
- data/lib/heitt/database.rb +276 -1782
- data/lib/heitt/decoder.rb +48 -0
- data/lib/heitt/formatter.rb +131 -0
- data/lib/heitt/grouper.rb +20 -0
- data/lib/heitt/profiles.rb +184 -0
- data/lib/heitt/scanner.rb +62 -0
- data/lib/heitt/utils.rb +57 -0
- data/lib/heitt/version.rb +3 -2
- data/lib/heitt.rb +15 -364
- metadata +17 -7
data/lib/heitt.rb
CHANGED
|
@@ -1,367 +1,18 @@
|
|
|
1
|
-
require 'json'
|
|
2
|
-
require 'set'
|
|
3
|
-
require 'strscan'
|
|
4
|
-
require '
|
|
1
|
+
#require 'json'
|
|
2
|
+
#require 'set'
|
|
3
|
+
#require 'strscan'
|
|
4
|
+
#require 'logger'
|
|
5
|
+
#require 'colorize'
|
|
6
|
+
require_relative 'heitt/profiles'
|
|
7
|
+
require_relative 'heitt/decoder'
|
|
5
8
|
require_relative 'heitt/database'
|
|
9
|
+
require_relative 'heitt/analyzer'
|
|
10
|
+
require_relative 'heitt/scanner'
|
|
11
|
+
require_relative 'heitt/grouper'
|
|
12
|
+
require_relative 'heitt/formatter'
|
|
6
13
|
require_relative 'heitt/version'
|
|
7
14
|
|
|
8
|
-
module HEITT
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
colored = text.colorize(color)
|
|
14
|
-
styles.each do |style|
|
|
15
|
-
colored = colored.send(style)
|
|
16
|
-
end
|
|
17
|
-
colored
|
|
18
|
-
end
|
|
19
|
-
end
|
|
20
|
-
#private_constant :Color
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
module Grouper
|
|
24
|
-
|
|
25
|
-
def self.group(results)
|
|
26
|
-
clusters = {}
|
|
27
|
-
|
|
28
|
-
clusters = results.group_by {|r| r[:candidates].first[:name]}
|
|
29
|
-
groups = clusters.each_with_index.map do |(name, group), index|
|
|
30
|
-
hashes = group.map {|r| r[:hash]}
|
|
31
|
-
{
|
|
32
|
-
cluster_id: index+1,
|
|
33
|
-
hashes: hashes,
|
|
34
|
-
candidates: group.first[:candidates],
|
|
35
|
-
count: hashes.size
|
|
36
|
-
}
|
|
37
|
-
end
|
|
38
|
-
groups
|
|
39
|
-
end
|
|
40
|
-
end
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
module Analyzer
|
|
45
|
-
def self.analyze(text, database: HEITT::DATABASE)
|
|
46
|
-
keyword_counts = keyword_counts(text.downcase, database: database)
|
|
47
|
-
algorithm_scores(keyword_counts, database: database)
|
|
48
|
-
end
|
|
49
|
-
|
|
50
|
-
def self.extract_prefix(text, offset)
|
|
51
|
-
line_start = text.rindex("\n", offset) || 0
|
|
52
|
-
text[line_start...offset]
|
|
53
|
-
end
|
|
54
|
-
|
|
55
|
-
def self.high_entropy?(text, min_ent)
|
|
56
|
-
entropy(text) >= min_ent
|
|
57
|
-
end
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
def self.score_candidates(modes, delim_prefix, context_scores)
|
|
61
|
-
prefix_matched_mode = nil
|
|
62
|
-
#context based scoring
|
|
63
|
-
matches = modes.map do |mode|
|
|
64
|
-
score_data = context_scores[mode[:name]]
|
|
65
|
-
score = score_data || 0
|
|
66
|
-
|
|
67
|
-
if prefix_match?(mode, delim_prefix)
|
|
68
|
-
#boost score as confidence is high if prefix matched
|
|
69
|
-
prefix_matched_mode = mode[:name]
|
|
70
|
-
score += 20
|
|
71
|
-
end
|
|
72
|
-
{
|
|
73
|
-
name: mode[:name],
|
|
74
|
-
hashcat: mode[:hashcat],
|
|
75
|
-
john: mode[:john],
|
|
76
|
-
description: mode[:description],
|
|
77
|
-
extended: mode[:extended],
|
|
78
|
-
score: score
|
|
79
|
-
}
|
|
80
|
-
end
|
|
81
|
-
return [] if matches.empty?
|
|
82
|
-
|
|
83
|
-
#calculate confidence
|
|
84
|
-
scores_hash = matches.map {|m| [m[:name], m[:score]]}.to_h
|
|
85
|
-
|
|
86
|
-
confidences = assign_confidence(scores_hash, prefix_matched_mode)
|
|
87
|
-
matches.map{|m| m.merge(confidence: confidences[m[:name]])}.sort_by {|m| -m[:score]}
|
|
88
|
-
end
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
private
|
|
92
|
-
def self.get_modes(entry)
|
|
93
|
-
entry[:modes] || entry[:algorithms] || entry[:hashes] ||
|
|
94
|
-
entry[:candidates] || entry[:types] || entry[:hashtypes]
|
|
95
|
-
end
|
|
96
|
-
|
|
97
|
-
#this code is an inspiration of "https://github.com/chrisjchandler/entropy/blob/main/entropy.go"
|
|
98
|
-
def self.entropy(text)
|
|
99
|
-
frequency = Hash.new(0)
|
|
100
|
-
text.each_char { |ch| frequency[ch] += 1 }
|
|
101
|
-
|
|
102
|
-
#calculate the total number of characters
|
|
103
|
-
total = text.length.to_f
|
|
104
|
-
#caluclate entropy
|
|
105
|
-
entropy = 0.0
|
|
106
|
-
frequency.each_value do |count|
|
|
107
|
-
probability = count.to_f / total
|
|
108
|
-
entropy += probability * Math.log2(probability)
|
|
109
|
-
end
|
|
110
|
-
#negate the sum as entropy is positive
|
|
111
|
-
-entropy
|
|
112
|
-
end
|
|
113
|
-
|
|
114
|
-
def self.keyword_counts(content_lower, database: HEITT::DATABASE)
|
|
115
|
-
keywords = database.flat_map do |entry|
|
|
116
|
-
modes = get_modes(entry)
|
|
117
|
-
next [] unless modes
|
|
118
|
-
modes.flat_map {|mode| mode[:context] || []}
|
|
119
|
-
end.uniq.map(&:downcase)
|
|
120
|
-
|
|
121
|
-
counts = {}
|
|
122
|
-
keywords.each do |kw|
|
|
123
|
-
count = content_lower.scan(/\b#{Regexp.escape(kw)}\b/).size
|
|
124
|
-
counts[kw] = count if count > 0
|
|
125
|
-
end
|
|
126
|
-
counts
|
|
127
|
-
end
|
|
128
|
-
|
|
129
|
-
|
|
130
|
-
def self.algorithm_scores(keyword_counts, database: HEITT::DATABASE)
|
|
131
|
-
scores = {}
|
|
132
|
-
return scores if keyword_counts.nil?
|
|
133
|
-
|
|
134
|
-
database.each do |entry|
|
|
135
|
-
modes = get_modes(entry)
|
|
136
|
-
next unless modes
|
|
137
|
-
modes.each do |mode|
|
|
138
|
-
contexts = mode[:context] || []
|
|
139
|
-
next if contexts.empty?
|
|
140
|
-
total = contexts.sum {|kw| keyword_counts[kw.downcase] || 0}
|
|
141
|
-
scores[mode[:name]] = total if total > 0
|
|
142
|
-
end
|
|
143
|
-
end
|
|
144
|
-
scores
|
|
145
|
-
end
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
def self.prefix_match?(mode, delim_prefix)
|
|
149
|
-
prefixes = mode[:prefixes] || []
|
|
150
|
-
return false if prefixes.empty?
|
|
151
|
-
|
|
152
|
-
delimiters = "= : "
|
|
153
|
-
raw_prefix = delim_prefix.strip.split(/[#{Regexp.escape(delimiters)}]/).last&.strip&.downcase
|
|
154
|
-
prefixes.map(&:downcase).include?(raw_prefix)
|
|
155
|
-
end
|
|
156
|
-
|
|
157
|
-
|
|
158
|
-
def self.assign_confidence(scores_hash, prefix_matched_mode=nil)
|
|
159
|
-
all_scores = scores_hash.values
|
|
160
|
-
|
|
161
|
-
return {} if all_scores.empty?
|
|
162
|
-
|
|
163
|
-
avg_score = all_scores.sum.to_f / all_scores.size
|
|
164
|
-
|
|
165
|
-
scores_hash.transform_values do |score|
|
|
166
|
-
if score == 0
|
|
167
|
-
"regex-match"
|
|
168
|
-
else
|
|
169
|
-
mode_name = scores_hash.key(score)
|
|
170
|
-
is_prefix_mode = (prefix_matched_mode == mode_name)
|
|
171
|
-
deviation = (score - avg_score) / avg_score
|
|
172
|
-
|
|
173
|
-
case deviation
|
|
174
|
-
when 2.0..Float::INFINITY
|
|
175
|
-
"high"
|
|
176
|
-
when 0.5..2.0
|
|
177
|
-
is_prefix_mode ? "high" : "medium-high"
|
|
178
|
-
else
|
|
179
|
-
is_prefix_mode ? "medium-high" : "medium-low"
|
|
180
|
-
end
|
|
181
|
-
end
|
|
182
|
-
end
|
|
183
|
-
end
|
|
184
|
-
end
|
|
185
|
-
#private_constant :Analyzer
|
|
186
|
-
|
|
187
|
-
|
|
188
|
-
|
|
189
|
-
module Scanner
|
|
190
|
-
|
|
191
|
-
def self.scan(input, database: HEITT::DATABASE, min_entropy: 3.5)
|
|
192
|
-
text = File.exist?(input) ? File.read(input) : input
|
|
193
|
-
context_scores = HEITT::Analyzer.analyze(text, database: database)
|
|
194
|
-
found = {}#[]
|
|
195
|
-
seen = {}
|
|
196
|
-
|
|
197
|
-
|
|
198
|
-
database.each do |entry|
|
|
199
|
-
regex = get_regex(entry)
|
|
200
|
-
modes = get_modes(entry)
|
|
201
|
-
next unless regex && modes && !modes.empty?
|
|
202
|
-
pattern = regex.is_a?(Regexp) ? regex : Regexp.new(regex)
|
|
203
|
-
scanner = StringScanner.new(text)
|
|
204
|
-
|
|
205
|
-
while scanner.scan_until(pattern)
|
|
206
|
-
matched = scanner.matched
|
|
207
|
-
next unless matched.length < 8 || HEITT::Analyzer.high_entropy?(matched, min_entropy)
|
|
208
|
-
offset = scanner.pos - matched.length
|
|
209
|
-
delim_prefix = HEITT::Analyzer.extract_prefix(text, offset)
|
|
210
|
-
|
|
211
|
-
candidates = HEITT::Analyzer.score_candidates(modes, delim_prefix, context_scores)
|
|
212
|
-
score = candidates.first[:score]
|
|
213
|
-
|
|
214
|
-
found[matched] ||= {hash: matched, candidates: []}
|
|
215
|
-
found[matched][:candidates].concat(candidates)
|
|
216
|
-
end
|
|
217
|
-
end
|
|
218
|
-
|
|
219
|
-
found.each_value do |result|
|
|
220
|
-
result[:candidates] = result[:candidates]
|
|
221
|
-
.group_by {|c| c[:name]}
|
|
222
|
-
.map {|name, dupes| dupes.max_by {|c| c[:score]}}
|
|
223
|
-
.sort_by {|c| -c[:score]}
|
|
224
|
-
|
|
225
|
-
# Re-assign confidence based on final merged scores
|
|
226
|
-
scores_hash = result[:candidates].map {|c| [c[:name], c[:score]]}.to_h
|
|
227
|
-
confidences = Analyzer.assign_confidence(scores_hash)
|
|
228
|
-
result[:candidates] = result[:candidates].map {|c| c.merge(confidence: confidences[c[:name]])}
|
|
229
|
-
end
|
|
230
|
-
found.values
|
|
231
|
-
end
|
|
232
|
-
|
|
233
|
-
private
|
|
234
|
-
|
|
235
|
-
def self.get_regex(entry)
|
|
236
|
-
entry[:extract_regex] || entry[:regex] || entry[:pattern] || entry[:regexp]
|
|
237
|
-
end
|
|
238
|
-
|
|
239
|
-
def self.get_modes(entry)
|
|
240
|
-
entry[:modes] || entry[:algorithms] || entry[:hashes] ||
|
|
241
|
-
entry[:candidates] || entry[:types] || entry[:hashtypes]
|
|
242
|
-
end
|
|
243
|
-
end
|
|
244
|
-
|
|
245
|
-
|
|
246
|
-
module Formatter
|
|
247
|
-
|
|
248
|
-
|
|
249
|
-
def self.tree(groups, verbose: false, extended: false, show_regex_match: false)
|
|
250
|
-
result = ""
|
|
251
|
-
|
|
252
|
-
#Filter out groups with extended candidates as true
|
|
253
|
-
visible_groups = groups.select do |group|
|
|
254
|
-
has_non_extended = group[:candidates].any? {|c| !c[:extended] || extended}
|
|
255
|
-
has_non_regex = group[:candidates].any? {|c| c[:confidence] != "regex-match" || show_regex_match}
|
|
256
|
-
has_non_extended && has_non_regex
|
|
257
|
-
end
|
|
258
|
-
#Renumber after filtering
|
|
259
|
-
renumbered_groups= visible_groups.each_with_index.map { |group, index| group.merge(cluster_id: index + 1) }
|
|
260
|
-
|
|
261
|
-
root = {
|
|
262
|
-
text: "#{HEITT::Color.colorize("\n\n[", :bold, :blue)}#{HEITT::Color.colorize("CLUSTERED HASHES", :green)}#{HEITT::Color.colorize("]", :bold, :blue)}",
|
|
263
|
-
children: renumbered_groups.map do |group|
|
|
264
|
-
{
|
|
265
|
-
text: HEITT::Color.colorize("HASH CLUSTER #{group[:cluster_id]}", :magenta, :bold),
|
|
266
|
-
children: group[:hashes].map{|h| {text: h, children: []}}
|
|
267
|
-
}
|
|
268
|
-
end
|
|
269
|
-
}
|
|
270
|
-
|
|
271
|
-
result += render_tree([root])
|
|
272
|
-
|
|
273
|
-
renumbered_groups.each do |group|
|
|
274
|
-
result += "#{HEITT::Color.colorize("\n\n[", :bold, :blue)}#{HEITT::Color.colorize("HASH CLUSTER #{group[:cluster_id]}", :white, :bold)}#{HEITT::Color.colorize("]\n", :bold, :blue)}"#, children: []}
|
|
275
|
-
candidate_nodes = (group[:candidates]).each_with_index.map do |candidate, idx|
|
|
276
|
-
next if candidate.nil?
|
|
277
|
-
next if candidate[:name].nil?
|
|
278
|
-
next if candidate[:extended] && !extended
|
|
279
|
-
next if candidate[:confidence] == "regex-match" && !show_regex_match
|
|
280
|
-
confidence = candidate[:confidence] ? " — CONFIDENCE: #{candidate[:confidence].upcase}" : ""
|
|
281
|
-
|
|
282
|
-
children = [
|
|
283
|
-
{text: "Hashcat Mode: #{candidate[:hashcat] || "--"}", children: []},
|
|
284
|
-
{text: "John Format: #{candidate[:john] || "--"}", children: []}
|
|
285
|
-
]
|
|
286
|
-
|
|
287
|
-
if verbose
|
|
288
|
-
if candidate[:description] && !candidate[:description].empty?
|
|
289
|
-
children << {text: "Description: #{candidate[:description]}", children: []}
|
|
290
|
-
end
|
|
291
|
-
|
|
292
|
-
if candidate[:notes] && !candidate[:notes].empty?
|
|
293
|
-
children << {text: "Notes:", children: candidate[:notes].map {|note| {text: note, children: []}}}
|
|
294
|
-
end
|
|
295
|
-
end
|
|
296
|
-
{
|
|
297
|
-
text: "#{HEITT::Color.colorize("[", :bold, :blue)}#{HEITT::Color.colorize("CANDIDATE #{idx + 1}: ", :bold, :cyan)}#{HEITT::Color.colorize("#{candidate[:name]}#{confidence}", :bold, :cyan)}#{HEITT::Color.colorize("]", :bold, :blue)}",
|
|
298
|
-
children: children
|
|
299
|
-
}
|
|
300
|
-
end.compact
|
|
301
|
-
result += render_tree(candidate_nodes, "", false, false) unless candidate_nodes.nil? || candidate_nodes.empty?
|
|
302
|
-
end
|
|
303
|
-
result
|
|
304
|
-
end
|
|
305
|
-
|
|
306
|
-
def self.json(groups, extended: false, show_regex_match: false)
|
|
307
|
-
visible_groups = groups.select do |group|
|
|
308
|
-
has_non_extended = group[:candidates].any? {|c| c[:extended] || extended}
|
|
309
|
-
has_non_regex = group[:candidates].any? {|c| c[:confidence] != "regex-match" || show_regex_match}
|
|
310
|
-
has_non_extended && has_non_regex
|
|
311
|
-
end
|
|
312
|
-
#Renumber after filtering
|
|
313
|
-
renumbered_groups = visible_groups.each_with_index.map { |group, index| group.merge(cluster_id: index+1)}
|
|
314
|
-
|
|
315
|
-
JSON.pretty_generate(
|
|
316
|
-
renumbered_groups.map do |group|
|
|
317
|
-
visible_candidates = group[:candidates].select do |c|
|
|
318
|
-
(!c[:extended] || extended) && (c[:confidence] != "regex-match" || show_regex_match)
|
|
319
|
-
end
|
|
320
|
-
{
|
|
321
|
-
cluster_id: group[:cluster_id],
|
|
322
|
-
count: group[:count],
|
|
323
|
-
hashes: group[:hashes],
|
|
324
|
-
candidates: visible_candidates.map do |candidate|
|
|
325
|
-
{
|
|
326
|
-
name: candidate[:name],
|
|
327
|
-
hashcat: candidate[:hashcat],
|
|
328
|
-
john: candidate[:john],
|
|
329
|
-
confidence: candidate[:confidence],
|
|
330
|
-
description: candidate[:description]
|
|
331
|
-
}
|
|
332
|
-
end
|
|
333
|
-
}
|
|
334
|
-
end
|
|
335
|
-
)
|
|
336
|
-
end
|
|
337
|
-
|
|
338
|
-
private
|
|
339
|
-
def self.render_tree(items, prefix = "", parent_is_last=true, is_root=true)
|
|
340
|
-
result = ""
|
|
341
|
-
|
|
342
|
-
items.each_with_index do |node, i|
|
|
343
|
-
is_last_item = (i == items.length - 1)
|
|
344
|
-
|
|
345
|
-
line = if is_root
|
|
346
|
-
"#{node[:text]}\n"
|
|
347
|
-
else
|
|
348
|
-
"#{HEITT::Color.colorize(prefix, :blue)}#{HEITT::Color.colorize((is_last_item ? '└── ' : '├── '), :blue)}#{node[:text]}\n"
|
|
349
|
-
end
|
|
350
|
-
|
|
351
|
-
child_prefix = if is_root
|
|
352
|
-
""
|
|
353
|
-
else
|
|
354
|
-
"#{HEITT::Color.colorize(prefix, :bold, :blue)}#{HEITT::Color.colorize((is_last_item ? " " : "│ "), :bold, :blue)}"
|
|
355
|
-
end
|
|
356
|
-
result += line
|
|
357
|
-
result += render_tree(node[:children], child_prefix, is_last_item, false) if node[:children].any?
|
|
358
|
-
|
|
359
|
-
if is_last_item && !is_root and !node[:children].any?
|
|
360
|
-
result += "#{HEITT::Color.colorize(prefix, :bold, :blue)} \n"
|
|
361
|
-
end
|
|
362
|
-
end
|
|
363
|
-
result
|
|
364
|
-
end
|
|
365
|
-
end
|
|
366
|
-
end
|
|
367
|
-
|
|
15
|
+
# module HEITT
|
|
16
|
+
# something like heitt = HEITT.new(database: nil, profiles: nil)
|
|
17
|
+
# heitt.identify("hash_string")
|
|
18
|
+
|
metadata
CHANGED
|
@@ -1,13 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: heitt
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.5.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Jonathan Botchway Owusu
|
|
8
|
+
autorequire:
|
|
8
9
|
bindir: bin
|
|
9
10
|
cert_chain: []
|
|
10
|
-
date:
|
|
11
|
+
date: 2026-08-30 00:00:00.000000000 Z
|
|
11
12
|
dependencies:
|
|
12
13
|
- !ruby/object:Gem::Dependency
|
|
13
14
|
name: colorize
|
|
@@ -33,14 +34,22 @@ extra_rdoc_files: []
|
|
|
33
34
|
files:
|
|
34
35
|
- bin/heitt
|
|
35
36
|
- lib/heitt.rb
|
|
37
|
+
- lib/heitt/analyzer.rb
|
|
36
38
|
- lib/heitt/database.rb
|
|
39
|
+
- lib/heitt/decoder.rb
|
|
40
|
+
- lib/heitt/formatter.rb
|
|
41
|
+
- lib/heitt/grouper.rb
|
|
42
|
+
- lib/heitt/profiles.rb
|
|
43
|
+
- lib/heitt/scanner.rb
|
|
44
|
+
- lib/heitt/utils.rb
|
|
37
45
|
- lib/heitt/version.rb
|
|
38
|
-
homepage: https://
|
|
46
|
+
homepage: https://codeberg.org/jobotow/heitt
|
|
39
47
|
licenses: []
|
|
40
48
|
metadata:
|
|
41
|
-
homepage_uri: https://
|
|
42
|
-
source_code_uri: https://
|
|
43
|
-
changelog_uri: https://
|
|
49
|
+
homepage_uri: https://codeberg.org/jobotow/heitt
|
|
50
|
+
source_code_uri: https://codeberg.org/jobotow/heitt
|
|
51
|
+
changelog_uri: https://codeberg.org/jobotow/heitt/blob/main/CHANGELOG.md
|
|
52
|
+
post_install_message:
|
|
44
53
|
rdoc_options: []
|
|
45
54
|
require_paths:
|
|
46
55
|
- lib
|
|
@@ -55,7 +64,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
55
64
|
- !ruby/object:Gem::Version
|
|
56
65
|
version: '0'
|
|
57
66
|
requirements: []
|
|
58
|
-
rubygems_version: 3.
|
|
67
|
+
rubygems_version: 3.4.20
|
|
68
|
+
signing_key:
|
|
59
69
|
specification_version: 4
|
|
60
70
|
summary: Hash Extraction, Identification and Triage Tool.
|
|
61
71
|
test_files: []
|