keyhound 0.2.0__tar.gz

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.
keyhound-0.2.0/LICENSE ADDED
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
keyhound-0.2.0/NOTICE ADDED
@@ -0,0 +1,4 @@
1
+ Keyhound
2
+ Copyright 2026 Felipe Henrique Maestrello De Lyra Convento
3
+
4
+ This product includes software developed by Felipe Henrique Maestrello De Lyra Convento
@@ -0,0 +1,129 @@
1
+ Metadata-Version: 2.4
2
+ Name: keyhound
3
+ Version: 0.2.0
4
+ Summary: Find exposed credentials in your code, with rules for Brazilian payment gateways and services
5
+ Author: Felipe Convento
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/felipedelyra-arch/keyhound
8
+ Project-URL: Repository, https://github.com/felipedelyra-arch/keyhound
9
+ Project-URL: Issues, https://github.com/felipedelyra-arch/keyhound/issues
10
+ Keywords: security,secrets,sast,credentials,brasil,pix,supabase
11
+ Classifier: Development Status :: 3 - Alpha
12
+ Classifier: Environment :: Console
13
+ Classifier: Intended Audience :: Developers
14
+ Classifier: Programming Language :: Python :: 3.11
15
+ Classifier: Programming Language :: Python :: 3.12
16
+ Classifier: Topic :: Security
17
+ Classifier: Natural Language :: Portuguese (Brazilian)
18
+ Requires-Python: >=3.11
19
+ Description-Content-Type: text/markdown
20
+ License-File: LICENSE
21
+ License-File: NOTICE
22
+ Requires-Dist: typer>=0.12
23
+ Requires-Dist: rich>=13.7
24
+ Provides-Extra: dev
25
+ Requires-Dist: pytest>=8.0; extra == "dev"
26
+ Dynamic: license-file
27
+
28
+ # Keyhound
29
+
30
+ Detector de credenciais expostas em código, com cobertura para serviços
31
+ brasileiros que ferramentas como gitleaks e trufflehog não reconhecem:
32
+ Mercado Pago, Asaas, Pagar.me, Cielo, PagSeguro, chave Pix, certificado
33
+ digital A1 e a chave `service_role` do Supabase.
34
+
35
+ ![Keyhound em funcionamento](demo.png)
36
+
37
+ ## Por que existe
38
+
39
+ Durante o desenvolvimento é comum colar a chave direto no arquivo para
40
+ testar — e esquecer. O código vai para o repositório e a chave vai junto.
41
+ Há robôs varrendo o GitHub atrás exatamente disso: o intervalo entre
42
+ publicar e a chave ser usada por terceiros costuma ser de minutos.
43
+
44
+ Remover a chave do arquivo não resolve: ela continua no histórico do Git,
45
+ recuperável por qualquer pessoa com acesso ao repositório.
46
+
47
+ ## Instalação
48
+
49
+ ```bash
50
+ pip install keyhound
51
+ ```
52
+
53
+ Requer Python 3.11 ou superior.
54
+
55
+ ## Uso
56
+
57
+ ```bash
58
+ keyhound scan . # varre o diretório atual
59
+ keyhound scan ./src -m high # só severidade alta ou acima
60
+ keyhound scan . -f json # saída para pipeline
61
+ keyhound scan . --fail-on critical # sai com código 1 se achar crítico
62
+
63
+ keyhound history . # varre todo o histórico do git
64
+ keyhound history . -n 100 # só os 100 commits mais recentes
65
+ keyhound history . -f json
66
+ ```
67
+
68
+ O valor do segredo é sempre mascarado na saída — na tela, no JSON e em
69
+ qualquer log.
70
+
71
+ ### Na integração contínua
72
+
73
+ ```bash
74
+ keyhound scan . --fail-on critical
75
+ ```
76
+
77
+ Código de saída `1` quando encontra algo no nível informado, `0` quando
78
+ está limpo.
79
+
80
+ ## O que detecta
81
+
82
+ **Globais** — AWS, GitHub, Slack, chave privada PEM, JWT, string de
83
+ conexão de banco, Google API, Stripe, senha e token em atribuição literal.
84
+
85
+ **Brasileiros** — Mercado Pago, Asaas, Pagar.me/Stone, MerchantKey da
86
+ Cielo, token do PagSeguro/PagBank, `service_role` e chave secreta do
87
+ Supabase, chave Pix aleatória (EVP) e senha de certificado A1.
88
+
89
+ A regra do `service_role` merece destaque: essa chave ignora todas as
90
+ políticas de Row Level Security do Supabase. Vazada no frontend, expõe o
91
+ banco inteiro. É visualmente idêntica à chave `anon`, que é pública e
92
+ inofensiva — o Keyhound distingue as duas.
93
+
94
+ ## Reduzindo ruído
95
+
96
+ Ferramenta que grita demais é desinstalada. O Keyhound filtra em três
97
+ camadas antes de reportar:
98
+
99
+ - caminhos listados no `.keyhoundignore`
100
+ - valores que são claramente placeholder (`xxxx`, `<your-key>`,
101
+ `${API_KEY}`, `CHANGEME`)
102
+ - chaves de exemplo que circulam em documentação oficial
103
+
104
+ Crie um `.keyhoundignore` na raiz do projeto:
105
+
106
+ ```
107
+ tests/fixtures/
108
+ **/*.lock
109
+ docs/exemplos/
110
+ ```
111
+
112
+ ## Desenvolvimento
113
+
114
+ ```bash
115
+ git clone https://github.com/felipedelyra-arch/keyhound.git
116
+ cd keyhound
117
+ python -m venv .venv && source .venv/bin/activate
118
+ pip install -e ".[dev]"
119
+ pytest
120
+ ```
121
+
122
+ ## Contribuindo
123
+
124
+ Veja [CONTRIBUTING.md](CONTRIBUTING.md). Regras novas para serviços
125
+ brasileiros são especialmente bem-vindas.
126
+
127
+ ## Licença
128
+
129
+ Apache License 2.0 — veja [LICENSE](LICENSE).
@@ -0,0 +1,102 @@
1
+ # Keyhound
2
+
3
+ Detector de credenciais expostas em código, com cobertura para serviços
4
+ brasileiros que ferramentas como gitleaks e trufflehog não reconhecem:
5
+ Mercado Pago, Asaas, Pagar.me, Cielo, PagSeguro, chave Pix, certificado
6
+ digital A1 e a chave `service_role` do Supabase.
7
+
8
+ ![Keyhound em funcionamento](demo.png)
9
+
10
+ ## Por que existe
11
+
12
+ Durante o desenvolvimento é comum colar a chave direto no arquivo para
13
+ testar — e esquecer. O código vai para o repositório e a chave vai junto.
14
+ Há robôs varrendo o GitHub atrás exatamente disso: o intervalo entre
15
+ publicar e a chave ser usada por terceiros costuma ser de minutos.
16
+
17
+ Remover a chave do arquivo não resolve: ela continua no histórico do Git,
18
+ recuperável por qualquer pessoa com acesso ao repositório.
19
+
20
+ ## Instalação
21
+
22
+ ```bash
23
+ pip install keyhound
24
+ ```
25
+
26
+ Requer Python 3.11 ou superior.
27
+
28
+ ## Uso
29
+
30
+ ```bash
31
+ keyhound scan . # varre o diretório atual
32
+ keyhound scan ./src -m high # só severidade alta ou acima
33
+ keyhound scan . -f json # saída para pipeline
34
+ keyhound scan . --fail-on critical # sai com código 1 se achar crítico
35
+
36
+ keyhound history . # varre todo o histórico do git
37
+ keyhound history . -n 100 # só os 100 commits mais recentes
38
+ keyhound history . -f json
39
+ ```
40
+
41
+ O valor do segredo é sempre mascarado na saída — na tela, no JSON e em
42
+ qualquer log.
43
+
44
+ ### Na integração contínua
45
+
46
+ ```bash
47
+ keyhound scan . --fail-on critical
48
+ ```
49
+
50
+ Código de saída `1` quando encontra algo no nível informado, `0` quando
51
+ está limpo.
52
+
53
+ ## O que detecta
54
+
55
+ **Globais** — AWS, GitHub, Slack, chave privada PEM, JWT, string de
56
+ conexão de banco, Google API, Stripe, senha e token em atribuição literal.
57
+
58
+ **Brasileiros** — Mercado Pago, Asaas, Pagar.me/Stone, MerchantKey da
59
+ Cielo, token do PagSeguro/PagBank, `service_role` e chave secreta do
60
+ Supabase, chave Pix aleatória (EVP) e senha de certificado A1.
61
+
62
+ A regra do `service_role` merece destaque: essa chave ignora todas as
63
+ políticas de Row Level Security do Supabase. Vazada no frontend, expõe o
64
+ banco inteiro. É visualmente idêntica à chave `anon`, que é pública e
65
+ inofensiva — o Keyhound distingue as duas.
66
+
67
+ ## Reduzindo ruído
68
+
69
+ Ferramenta que grita demais é desinstalada. O Keyhound filtra em três
70
+ camadas antes de reportar:
71
+
72
+ - caminhos listados no `.keyhoundignore`
73
+ - valores que são claramente placeholder (`xxxx`, `<your-key>`,
74
+ `${API_KEY}`, `CHANGEME`)
75
+ - chaves de exemplo que circulam em documentação oficial
76
+
77
+ Crie um `.keyhoundignore` na raiz do projeto:
78
+
79
+ ```
80
+ tests/fixtures/
81
+ **/*.lock
82
+ docs/exemplos/
83
+ ```
84
+
85
+ ## Desenvolvimento
86
+
87
+ ```bash
88
+ git clone https://github.com/felipedelyra-arch/keyhound.git
89
+ cd keyhound
90
+ python -m venv .venv && source .venv/bin/activate
91
+ pip install -e ".[dev]"
92
+ pytest
93
+ ```
94
+
95
+ ## Contribuindo
96
+
97
+ Veja [CONTRIBUTING.md](CONTRIBUTING.md). Regras novas para serviços
98
+ brasileiros são especialmente bem-vindas.
99
+
100
+ ## Licença
101
+
102
+ Apache License 2.0 — veja [LICENSE](LICENSE).
@@ -0,0 +1,8 @@
1
+ """Keyhound — detector de credenciais expostas em código."""
2
+
3
+ __version__ = "0.2.0"
4
+
5
+ from keyhound.models import Finding, Rule, Severity
6
+ from keyhound.scanner import scan_directory
7
+
8
+ __all__ = ["Finding", "Rule", "Severity", "scan_directory", "__version__"]
@@ -0,0 +1,113 @@
1
+ from __future__ import annotations
2
+
3
+ from pathlib import Path
4
+ from typing import Annotated
5
+
6
+ import typer
7
+ from rich.console import Console
8
+
9
+ from keyhound import __version__
10
+ from keyhound.history import scan_history
11
+ from keyhound.models import Severity
12
+ from keyhound.report import (
13
+ history_to_json,
14
+ print_history_table,
15
+ print_summary,
16
+ print_table,
17
+ to_json,
18
+ )
19
+ from keyhound.rules import rules_by_severity
20
+ from keyhound.scanner import scan_directory
21
+
22
+ app = typer.Typer(
23
+ help="Keyhound — find exposed credentials in your code.",
24
+ no_args_is_help=True,
25
+ add_completion=False,
26
+ )
27
+ console = Console()
28
+ err_console = Console(stderr=True)
29
+
30
+
31
+ @app.command()
32
+ def scan(
33
+ path: Annotated[
34
+ Path, typer.Argument(help="Directory to scan.")
35
+ ] = Path("."),
36
+ min_severity: Annotated[
37
+ Severity,
38
+ typer.Option("--min-severity", "-m", help="Lowest severity to report."),
39
+ ] = Severity.LOW,
40
+ output_format: Annotated[
41
+ str, typer.Option("--format", "-f", help="table or json.")
42
+ ] = "table",
43
+ fail_on: Annotated[
44
+ Severity | None,
45
+ typer.Option("--fail-on", help="Exit with code 1 at this severity or above."),
46
+ ] = None,
47
+ ) -> None:
48
+ """Scan a directory for hardcoded secrets."""
49
+ root = path.resolve()
50
+ if not root.is_dir():
51
+ err_console.print(f"[bold red]Not a directory:[/] {root}")
52
+ raise typer.Exit(code=2)
53
+
54
+ findings = scan_directory(root, rules_by_severity(min_severity))
55
+
56
+ if output_format == "json":
57
+ console.print_json(to_json(findings, root))
58
+ else:
59
+ print_table(findings, root, console)
60
+ print_summary(findings, console)
61
+
62
+ if fail_on is not None and any(f.severity.weight >= fail_on.weight for f in findings):
63
+ raise typer.Exit(code=1)
64
+
65
+
66
+ @app.command()
67
+ def history(
68
+ path: Annotated[
69
+ Path, typer.Argument(help="Git repository to scan.")
70
+ ] = Path("."),
71
+ min_severity: Annotated[
72
+ Severity,
73
+ typer.Option("--min-severity", "-m", help="Lowest severity to report."),
74
+ ] = Severity.LOW,
75
+ limit: Annotated[
76
+ int | None,
77
+ typer.Option("--limit", "-n", help="Scan only the N most recent commits."),
78
+ ] = None,
79
+ output_format: Annotated[
80
+ str, typer.Option("--format", "-f", help="table or json.")
81
+ ] = "table",
82
+ fail_on: Annotated[
83
+ Severity | None,
84
+ typer.Option("--fail-on", help="Exit with code 1 at this severity or above."),
85
+ ] = None,
86
+ ) -> None:
87
+ """Scan the git history for secrets that were committed and later removed."""
88
+ root = path.resolve()
89
+ if not root.is_dir():
90
+ err_console.print(f"[bold red]Not a directory:[/] {root}")
91
+ raise typer.Exit(code=2)
92
+
93
+ items = scan_history(root, rules_by_severity(min_severity), max_commits=limit)
94
+
95
+ if output_format == "json":
96
+ console.print_json(history_to_json(items))
97
+ else:
98
+ print_history_table(items, console)
99
+
100
+ if fail_on is not None and any(
101
+ i.finding.severity.weight >= fail_on.weight for i in items
102
+ ):
103
+ raise typer.Exit(code=1)
104
+
105
+
106
+ @app.command()
107
+ def version() -> None:
108
+ """Show the version."""
109
+ console.print(f"keyhound {__version__}")
110
+
111
+
112
+ if __name__ == "__main__":
113
+ app()
@@ -0,0 +1,20 @@
1
+ import math
2
+ from collections import Counter
3
+
4
+ def shannon_entropy(s: str) -> float:
5
+
6
+ if not s:
7
+ return 0.0
8
+
9
+ total = len(s)
10
+ entropy = 0.0
11
+ for count in Counter(s).values():
12
+ p = count / total
13
+ entropy -= p * math.log2(p)
14
+ return entropy
15
+
16
+ def is_high_entropy(s: str, threshold: float = 3.5, min_length: int = 20) -> bool:
17
+
18
+ if len(s) < min_length:
19
+ return False
20
+ return shannon_entropy(s) >= threshold
@@ -0,0 +1,88 @@
1
+ """Anti-ruído: decide o que NÃO é segredo de verdade.
2
+
3
+ Três camadas, da mais barata para a mais cara:
4
+ 1. caminho ignorado pelo .keyhoundignore
5
+ 2. valor é placeholder óbvio (CHANGEME, xxxx, <your-key>)
6
+ 3. valor está na allowlist de exemplos públicos conhecidos
7
+ """
8
+
9
+ from __future__ import annotations
10
+
11
+ import fnmatch
12
+ import re
13
+ from pathlib import Path
14
+
15
+ IGNORE_FILE = ".keyhoundignore"
16
+
17
+ KNOWN_EXAMPLES: frozenset[str] = frozenset({
18
+ "AKIAIOSFODNN7EXAMPLE",
19
+ "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY",
20
+ # Chave de teste da documentação do Stripe, montada em partes para não
21
+ # disparar o push protection do GitHub.
22
+ "sk_test_" + "4eC39HqLyjWDarjt" + "T1zdp7dc",
23
+ })
24
+
25
+ PLACEHOLDER_PATTERNS: tuple[re.Pattern[str], ...] = tuple(
26
+ re.compile(p, re.IGNORECASE)
27
+ for p in (
28
+ r"^x{4,}$",
29
+ r"^\.{3,}$",
30
+ r"^<.+>$",
31
+ r"^\$\{?[A-Z_]+\}?$",
32
+ r"\b(?:change[_-]?me|your[_-]?\w+[_-]?here|replace[_-]?me)\b",
33
+ r"\b(?:example|sample|dummy|placeholder|fake)\b",
34
+ r"^(.)\1{7,}$",
35
+ )
36
+ )
37
+
38
+
39
+ def load_ignore_patterns(root: Path) -> list[str]:
40
+ """Lê o .keyhoundignore. Linha vazia e comentário são descartados."""
41
+ ignore_file = root / IGNORE_FILE
42
+ if not ignore_file.is_file():
43
+ return []
44
+
45
+ patterns: list[str] = []
46
+ for raw in ignore_file.read_text(encoding="utf-8", errors="ignore").splitlines():
47
+ line = raw.strip()
48
+ if not line or line.startswith("#"):
49
+ continue
50
+ patterns.append(line)
51
+ return patterns
52
+
53
+
54
+ def is_ignored_path(path: Path, root: Path, patterns: list[str]) -> bool:
55
+ """Casa o caminho relativo contra os globs do .keyhoundignore."""
56
+ if not patterns:
57
+ return False
58
+
59
+ try:
60
+ relative = path.relative_to(root).as_posix()
61
+ except ValueError:
62
+ return False
63
+
64
+ for pattern in patterns:
65
+ if pattern.endswith("/"):
66
+ if relative.startswith(pattern) or f"/{pattern}" in f"/{relative}":
67
+ return True
68
+ elif fnmatch.fnmatch(relative, pattern):
69
+ return True
70
+ elif fnmatch.fnmatch(relative, f"*/{pattern}"):
71
+ return True
72
+ return False
73
+
74
+
75
+ def is_placeholder(value: str) -> bool:
76
+ stripped = value.strip()
77
+ if not stripped:
78
+ return True
79
+ return any(p.search(stripped) for p in PLACEHOLDER_PATTERNS)
80
+
81
+
82
+ def is_known_example(value: str) -> bool:
83
+ return value.strip() in KNOWN_EXAMPLES
84
+
85
+
86
+ def is_noise(value: str) -> bool:
87
+ """Porta única usada pelo scanner."""
88
+ return is_placeholder(value) or is_known_example(value)