ciphergate-cli 0.7.0__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.
- ciphergate_cli-0.7.0/.gitignore +42 -0
- ciphergate_cli-0.7.0/CHANGELOG.md +272 -0
- ciphergate_cli-0.7.0/LICENSE +202 -0
- ciphergate_cli-0.7.0/NOTICE +4 -0
- ciphergate_cli-0.7.0/PKG-INFO +531 -0
- ciphergate_cli-0.7.0/README.md +492 -0
- ciphergate_cli-0.7.0/SECURITY.md +67 -0
- ciphergate_cli-0.7.0/docs/architecture.md +78 -0
- ciphergate_cli-0.7.0/docs/claude-code-tooling.md +69 -0
- ciphergate_cli-0.7.0/docs/detector-coverage.md +78 -0
- ciphergate_cli-0.7.0/docs/examples.md +64 -0
- ciphergate_cli-0.7.0/docs/limitations.md +94 -0
- ciphergate_cli-0.7.0/docs/policy-schema.md +173 -0
- ciphergate_cli-0.7.0/docs/security-and-privacy.md +110 -0
- ciphergate_cli-0.7.0/docs/threat-model.md +39 -0
- ciphergate_cli-0.7.0/examples/expected/sample.dev_local_dev.csv +4 -0
- ciphergate_cli-0.7.0/examples/expected/sample.dev_local_dev.json +34 -0
- ciphergate_cli-0.7.0/examples/expected/sample.dev_local_dev.jsonl +3 -0
- ciphergate_cli-0.7.0/examples/expected/sample.dev_local_dev.log +6 -0
- ciphergate_cli-0.7.0/examples/sample.csv +4 -0
- ciphergate_cli-0.7.0/examples/sample.json +26 -0
- ciphergate_cli-0.7.0/examples/sample.jsonl +3 -0
- ciphergate_cli-0.7.0/examples/sample.log +6 -0
- ciphergate_cli-0.7.0/policies/dev_local.yml +58 -0
- ciphergate_cli-0.7.0/policies/developer_logs.yml +97 -0
- ciphergate_cli-0.7.0/policies/external_ai.yml +66 -0
- ciphergate_cli-0.7.0/policies/financial_template.yml +83 -0
- ciphergate_cli-0.7.0/policies/healthcare_template.yml +95 -0
- ciphergate_cli-0.7.0/policies/local_debug.yml +41 -0
- ciphergate_cli-0.7.0/policies/multi_environment.yml +108 -0
- ciphergate_cli-0.7.0/policies/prd_external_ai.yml +102 -0
- ciphergate_cli-0.7.0/policies/stg_test.yml +68 -0
- ciphergate_cli-0.7.0/policies/test_dataset.yml +71 -0
- ciphergate_cli-0.7.0/pyproject.toml +116 -0
- ciphergate_cli-0.7.0/src/ciphergate/__init__.py +95 -0
- ciphergate_cli-0.7.0/src/ciphergate/__main__.py +6 -0
- ciphergate_cli-0.7.0/src/ciphergate/cli.py +832 -0
- ciphergate_cli-0.7.0/src/ciphergate/config.py +50 -0
- ciphergate_cli-0.7.0/src/ciphergate/constants.py +274 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/__init__.py +5 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/base.py +53 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/custom_regex.py +37 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/dates.py +92 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/email.py +56 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/field_names.py +220 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/ip_address.py +85 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/network.py +42 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/payment_card.py +77 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/phone.py +67 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/presidio_ner.py +112 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/regex_safety.py +40 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/registry.py +194 -0
- ciphergate_cli-0.7.0/src/ciphergate/detectors/secrets.py +130 -0
- ciphergate_cli-0.7.0/src/ciphergate/errors.py +119 -0
- ciphergate_cli-0.7.0/src/ciphergate/models/__init__.py +1 -0
- ciphergate_cli-0.7.0/src/ciphergate/models/context.py +69 -0
- ciphergate_cli-0.7.0/src/ciphergate/models/finding.py +108 -0
- ciphergate_cli-0.7.0/src/ciphergate/models/policy.py +402 -0
- ciphergate_cli-0.7.0/src/ciphergate/models/report.py +115 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/__init__.py +1 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/atomic_output.py +143 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/batch.py +533 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/inspector.py +282 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/paths.py +98 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/planner.py +192 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/rescan.py +120 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/sanitizer.py +392 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/stdio.py +173 -0
- ciphergate_cli-0.7.0/src/ciphergate/pipeline/streams.py +152 -0
- ciphergate_cli-0.7.0/src/ciphergate/policy/__init__.py +26 -0
- ciphergate_cli-0.7.0/src/ciphergate/policy/context.py +203 -0
- ciphergate_cli-0.7.0/src/ciphergate/policy/engine.py +194 -0
- ciphergate_cli-0.7.0/src/ciphergate/policy/loader.py +116 -0
- ciphergate_cli-0.7.0/src/ciphergate/policy/precedence.py +149 -0
- ciphergate_cli-0.7.0/src/ciphergate/policy/validator.py +632 -0
- ciphergate_cli-0.7.0/src/ciphergate/py.typed +0 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/__init__.py +113 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/accesslog_reader.py +244 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/base.py +131 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/csv_reader.py +241 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/json_reader.py +184 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/jsonl_reader.py +97 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/jsonlog_reader.py +178 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/line_structure.py +125 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/logfmt_reader.py +100 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/stacktrace_reader.py +103 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/syslog_reader.py +309 -0
- ciphergate_cli-0.7.0/src/ciphergate/readers/text_reader.py +59 -0
- ciphergate_cli-0.7.0/src/ciphergate/reporting/__init__.py +1 -0
- ciphergate_cli-0.7.0/src/ciphergate/reporting/audit.py +85 -0
- ciphergate_cli-0.7.0/src/ciphergate/reporting/safe_text.py +71 -0
- ciphergate_cli-0.7.0/src/ciphergate/reporting/serializer.py +44 -0
- ciphergate_cli-0.7.0/src/ciphergate/reporting/terminal.py +147 -0
- ciphergate_cli-0.7.0/src/ciphergate/templates/starter_policy.yml +77 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/__init__.py +6 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/date_shift.py +79 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/generalize.py +107 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/keys.py +177 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/pseudonymize.py +113 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/redact.py +9 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/registry.py +201 -0
- ciphergate_cli-0.7.0/src/ciphergate/transforms/replace.py +16 -0
- ciphergate_cli-0.7.0/tests/__init__.py +0 -0
- ciphergate_cli-0.7.0/tests/conftest.py +106 -0
- ciphergate_cli-0.7.0/tests/integration/__init__.py +0 -0
- ciphergate_cli-0.7.0/tests/integration/test_api_batch_streams.py +242 -0
- ciphergate_cli-0.7.0/tests/integration/test_atomic_output.py +192 -0
- ciphergate_cli-0.7.0/tests/integration/test_batch.py +356 -0
- ciphergate_cli-0.7.0/tests/integration/test_cli_e2e.py +348 -0
- ciphergate_cli-0.7.0/tests/integration/test_domain_templates.py +115 -0
- ciphergate_cli-0.7.0/tests/integration/test_environment_matrix.py +258 -0
- ciphergate_cli-0.7.0/tests/integration/test_pipelines.py +337 -0
- ciphergate_cli-0.7.0/tests/integration/test_stdio.py +299 -0
- ciphergate_cli-0.7.0/tests/regression/__init__.py +0 -0
- ciphergate_cli-0.7.0/tests/regression/test_known_cases.py +67 -0
- ciphergate_cli-0.7.0/tests/security/__init__.py +0 -0
- ciphergate_cli-0.7.0/tests/security/test_key_file.py +123 -0
- ciphergate_cli-0.7.0/tests/security/test_no_network.py +77 -0
- ciphergate_cli-0.7.0/tests/security/test_no_raw_value_leaks.py +154 -0
- ciphergate_cli-0.7.0/tests/security/test_path_safety.py +127 -0
- ciphergate_cli-0.7.0/tests/security/test_policy_fail_closed.py +88 -0
- ciphergate_cli-0.7.0/tests/security/test_review_findings.py +341 -0
- ciphergate_cli-0.7.0/tests/tooling/__init__.py +0 -0
- ciphergate_cli-0.7.0/tests/tooling/test_ci_supply_chain.py +65 -0
- ciphergate_cli-0.7.0/tests/tooling/test_claude_tooling.py +207 -0
- ciphergate_cli-0.7.0/tests/tooling/test_git_tooling.py +155 -0
- ciphergate_cli-0.7.0/tests/tooling/test_publish_workflow.py +71 -0
- ciphergate_cli-0.7.0/tests/unit/__init__.py +0 -0
- ciphergate_cli-0.7.0/tests/unit/test_accesslog.py +398 -0
- ciphergate_cli-0.7.0/tests/unit/test_detectors.py +392 -0
- ciphergate_cli-0.7.0/tests/unit/test_jsonlog.py +444 -0
- ciphergate_cli-0.7.0/tests/unit/test_logfmt.py +257 -0
- ciphergate_cli-0.7.0/tests/unit/test_policy_engine.py +369 -0
- ciphergate_cli-0.7.0/tests/unit/test_policy_precedence.py +212 -0
- ciphergate_cli-0.7.0/tests/unit/test_policy_validation.py +320 -0
- ciphergate_cli-0.7.0/tests/unit/test_presidio_ner.py +299 -0
- ciphergate_cli-0.7.0/tests/unit/test_properties.py +178 -0
- ciphergate_cli-0.7.0/tests/unit/test_readers.py +246 -0
- ciphergate_cli-0.7.0/tests/unit/test_stacktrace.py +370 -0
- ciphergate_cli-0.7.0/tests/unit/test_syslog.py +402 -0
- ciphergate_cli-0.7.0/tests/unit/test_transforms.py +349 -0
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
# Python / build
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[cod]
|
|
4
|
+
*.egg-info/
|
|
5
|
+
build/
|
|
6
|
+
dist/
|
|
7
|
+
.eggs/
|
|
8
|
+
# Virtual environments
|
|
9
|
+
.venv/
|
|
10
|
+
venv/
|
|
11
|
+
env/
|
|
12
|
+
# Tool caches and coverage
|
|
13
|
+
.pytest_cache/
|
|
14
|
+
.mypy_cache/
|
|
15
|
+
.ruff_cache/
|
|
16
|
+
.hypothesis/
|
|
17
|
+
.coverage
|
|
18
|
+
.coverage.*
|
|
19
|
+
coverage.xml
|
|
20
|
+
htmlcov/
|
|
21
|
+
# Secrets and keys (never commit)
|
|
22
|
+
.env
|
|
23
|
+
.env.*
|
|
24
|
+
!.env.example
|
|
25
|
+
*.key
|
|
26
|
+
*.pem
|
|
27
|
+
secrets/
|
|
28
|
+
# Local / real data and CipherGate outputs (keep synthetic examples/ and policies/)
|
|
29
|
+
data/
|
|
30
|
+
real_data/
|
|
31
|
+
*.sanitized.*
|
|
32
|
+
*.report.json
|
|
33
|
+
ciphergate-policy.yml
|
|
34
|
+
.ciphergate-*.tmp
|
|
35
|
+
# Claude Code machine-local settings
|
|
36
|
+
.claude/settings.local.json
|
|
37
|
+
# Editors / OS
|
|
38
|
+
.idea/
|
|
39
|
+
.vscode/
|
|
40
|
+
*.swp
|
|
41
|
+
.DS_Store
|
|
42
|
+
Thumbs.db
|
|
@@ -0,0 +1,272 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
All notable changes are documented here. Format: [Keep a Changelog](https://keepachangelog.com/);
|
|
4
|
+
versioning: [PEP 440](https://peps.python.org/pep-0440/) with SemVer meaning (pre-1.0: minor versions may break;
|
|
5
|
+
`aN` = alpha pre-release).
|
|
6
|
+
|
|
7
|
+
## [Unreleased]
|
|
8
|
+
|
|
9
|
+
## [0.7.0] - 2026-10-30
|
|
10
|
+
|
|
11
|
+
First release published to PyPI. CLI, API and policy behaviour are unchanged, except for the
|
|
12
|
+
corrected NER install hint below.
|
|
13
|
+
|
|
14
|
+
### Changed
|
|
15
|
+
|
|
16
|
+
- The PyPI distribution is now named `ciphergate-cli`, because `ciphergate` on PyPI is an
|
|
17
|
+
unrelated project. The import package and the `ciphergate` command are unchanged. The optional
|
|
18
|
+
NER extra is `ciphergate-cli[ner]`: the old hint `pip install 'ciphergate[ner]'` would have
|
|
19
|
+
installed that unrelated package.
|
|
20
|
+
|
|
21
|
+
### Added
|
|
22
|
+
|
|
23
|
+
- Release publishing workflow (`.github/workflows/publish.yml`). On each published GitHub
|
|
24
|
+
release it builds from the tag on a GitHub runner, checks and smoke-tests the files, and
|
|
25
|
+
attaches them with `SHA256SUMS`. After maintainer approval it uploads the same files to PyPI
|
|
26
|
+
with Trusted Publishing (no stored token).
|
|
27
|
+
|
|
28
|
+
## [0.6.1] - 2026-10-30
|
|
29
|
+
|
|
30
|
+
Starter-policy update for `--format stacktrace`. No code changes.
|
|
31
|
+
|
|
32
|
+
### Changed
|
|
33
|
+
|
|
34
|
+
- Starter policies: `dev_local` keeps stack-trace frames and source lines (`stack_trace`
|
|
35
|
+
detector) for local debugging. `developer_logs` keeps them for `local_dev`, `approved_internal`
|
|
36
|
+
and `production_monitoring` and redacts them for every other destination. Before, these
|
|
37
|
+
findings fell back to review with `--format stacktrace`. Other `proprietary.source` findings
|
|
38
|
+
are unchanged.
|
|
39
|
+
|
|
40
|
+
## [0.6.0] - 2026-10-30
|
|
41
|
+
|
|
42
|
+
Adds stack-trace-aware log input as `--format stacktrace`. Existing formats behave as before.
|
|
43
|
+
|
|
44
|
+
### Added
|
|
45
|
+
|
|
46
|
+
- Stack-trace format (#47): `--format stacktrace` scans each line like `text` and also
|
|
47
|
+
recognises Python tracebacks and JVM/Node.js frames. Frame and Python source lines get a
|
|
48
|
+
`proprietary.source` finding from the new `stack_trace` detector (`/stack/frames/N`,
|
|
49
|
+
`/stack/frames/N/source`), so policies can redact, review or block them; exception lines get
|
|
50
|
+
`/stack/exception` (`/stack/caused_by`, `/stack/suppressed`). No lookahead or buffering;
|
|
51
|
+
never selected from the file extension.
|
|
52
|
+
|
|
53
|
+
## [0.5.0] - 2026-10-29
|
|
54
|
+
|
|
55
|
+
Adds syslog (RFC 5424 and RFC 3164) and CEF parsing as `--format syslog`. Existing formats
|
|
56
|
+
behave as before; rescan additionally recognises CipherGate markers inside escaped fields.
|
|
57
|
+
|
|
58
|
+
### Added
|
|
59
|
+
|
|
60
|
+
- syslog/CEF format (#46): `--format syslog` for RFC 5424 and RFC 3164 lines (including rsyslog
|
|
61
|
+
files) and CEF records, bare or as a syslog message. Header fields, RFC 5424 structured-data
|
|
62
|
+
parameters (`/sd/<sd-id>/<name>`) and CEF headers and extensions (`/cef/extension/<key>`)
|
|
63
|
+
become fields. Short CEF keys get canonical names for the field-name heuristics (`suser`,
|
|
64
|
+
`src`, ...; `csN` via `csNLabel`) while findings keep the raw key. Escapes are decoded for
|
|
65
|
+
scanning and re-applied to replacements; every rewritten line must still parse.
|
|
66
|
+
|
|
67
|
+
### Changed
|
|
68
|
+
|
|
69
|
+
- Rescan recognises a field whose whole decoded value is a CipherGate marker or replacement,
|
|
70
|
+
even when a pattern matched only part of its escaped form (e.g. `[REDACTED:...\]` in syslog
|
|
71
|
+
structured data).
|
|
72
|
+
|
|
73
|
+
## [0.4.0] - 2026-10-29
|
|
74
|
+
|
|
75
|
+
Adds two structured log formats, JSON-in-log and nginx/Apache access logs, and fixes a phone
|
|
76
|
+
detection gap in logfmt. Existing formats behave as before, except that `remote_user` fields
|
|
77
|
+
are now classified as customer identifiers.
|
|
78
|
+
|
|
79
|
+
### Added
|
|
80
|
+
|
|
81
|
+
- JSON-in-log format (#39): `--format jsonlog` for log lines that embed JSON objects. Each line
|
|
82
|
+
is scanned exactly like `text`; embedded objects add field context (JSON Pointer paths,
|
|
83
|
+
field-name heuristics and policy classifications on keys, decoding of escaped values and
|
|
84
|
+
keys). Rewrites are JSON-escaped and re-validated; a rewrite that would break an embedded
|
|
85
|
+
object fails the run. Never selected from the file extension.
|
|
86
|
+
- Access-log format (#39): `--format accesslog` for nginx/Apache common and combined lines.
|
|
87
|
+
Fields get nginx variable names (`/remote_addr`, `/request/path`, `/http_user_agent`, ...),
|
|
88
|
+
query parameters of the request and referer become fields (`/request/query/<name>`), and log
|
|
89
|
+
escapes and percent-encoding are decoded for scanning. Replacements are re-encoded per field
|
|
90
|
+
and every rewritten line must still parse, or the run fails.
|
|
91
|
+
|
|
92
|
+
### Changed
|
|
93
|
+
|
|
94
|
+
- The `remote_user` field name is now classified as `pii.customer_identifier` in every format.
|
|
95
|
+
|
|
96
|
+
### Fixed
|
|
97
|
+
|
|
98
|
+
- Phone numbers inside a value whose field name implies email (for example
|
|
99
|
+
`email="call 202-555-0143"` in logfmt) are no longer suppressed by the whole-value field-name
|
|
100
|
+
finding.
|
|
101
|
+
|
|
102
|
+
## [0.3.0] - 2026-10-29
|
|
103
|
+
|
|
104
|
+
Adds the Python API for streams and directories, and fixes a macOS path-safety bug in
|
|
105
|
+
directory runs that shipped in 0.2.0. CLI behaviour on Linux and Windows is unchanged.
|
|
106
|
+
|
|
107
|
+
### Added
|
|
108
|
+
|
|
109
|
+
- Python API for streams and directories (#38): `inspect_stream`, `plan_stream`,
|
|
110
|
+
`rescan_stream` and `sanitize_stream` take binary streams (format required; input spooled to
|
|
111
|
+
a private, size-capped workspace; output written only after a successful run).
|
|
112
|
+
`inspect_directory`, `plan_directory`, `rescan_directory` and `sanitize_directory` expose
|
|
113
|
+
directory runs and return the newly exported `BatchReport`. `sanitize_directory` refuses
|
|
114
|
+
`force=True`, as the CLI does.
|
|
115
|
+
|
|
116
|
+
### Changed
|
|
117
|
+
|
|
118
|
+
- CI runs the test suite on macOS (py3.12) again (#37). Case-alias tests now run on any
|
|
119
|
+
case-insensitive filesystem instead of only on Windows.
|
|
120
|
+
|
|
121
|
+
### Fixed
|
|
122
|
+
|
|
123
|
+
- macOS: a directory run accepted an output directory inside the input directory when the
|
|
124
|
+
output path used a different letter case (`--output IN/out` for input `in`), because path
|
|
125
|
+
comparison relied on `normcase`, which does nothing on POSIX. The check now compares file
|
|
126
|
+
identity up the parent chain. The same applies to `--report` placement in directory runs.
|
|
127
|
+
Windows and Linux were not affected. Found by the new macOS CI job (#37).
|
|
128
|
+
|
|
129
|
+
## [0.2.0] - 2026-10-29
|
|
130
|
+
|
|
131
|
+
Feature release. Existing policies, reports and single-file behaviour are unchanged, except
|
|
132
|
+
where noted below.
|
|
133
|
+
|
|
134
|
+
### Added
|
|
135
|
+
|
|
136
|
+
- Optional local NER detector (#7): `pip install 'ciphergate[ner]'` plus a user-installed spaCy
|
|
137
|
+
model; enable with `detectors.presidio` in the policy (off by default). Presidio entities map
|
|
138
|
+
to categories (default `PERSON` -> `pii.person_name`, `LOCATION` -> `location.coarse`) and
|
|
139
|
+
findings use detector `presidio_ner`. A missing extra or model fails with exit 6 and is never
|
|
140
|
+
downloaded. Third-party error messages are replaced. Tested with a fake engine only.
|
|
141
|
+
- Directory (batch) runs (#9): `inspect`, `plan`, `rescan` and `sanitize` accept a directory
|
|
142
|
+
INPUT, with `--recursive` and `--max-files` (default 1000). Symlinks, junctions and special
|
|
143
|
+
files are skipped and reported, never followed. `sanitize` stages the whole output tree and
|
|
144
|
+
publishes a new directory only if every file was sanitized. Batch report schema
|
|
145
|
+
`ciphergate.batch-report/v1`; the exit code is the first failing file's. CLI only.
|
|
146
|
+
- logfmt format (#11): `--format logfmt` for `key=value` log lines. Each line is scanned exactly
|
|
147
|
+
like `text` (property-tested: never fewer findings), plus field context: findings inside a
|
|
148
|
+
value are attributed to that field (`/key`) and field-name heuristics run on keys, so policy
|
|
149
|
+
field rules apply to log fields. Lines are rewritten span by span, preserving quoting.
|
|
150
|
+
`drop_field` becomes `review`. In span transforms, each finding now uses its own field path
|
|
151
|
+
for pseudonym scope (unchanged for existing formats).
|
|
152
|
+
- Key files (#10): set `<key_env>_FILE` (e.g. `CIPHERGATE_HMAC_KEY_FILE`) to a key file path.
|
|
153
|
+
The file must be regular and at most 4 KiB; on POSIX it must be owned by the current user with
|
|
154
|
+
no group/other permissions (symlink targets are checked). Windows ACLs are not checked (a
|
|
155
|
+
warning is logged). Setting both sources is refused. Failures exit 6 (`key_file_invalid`)
|
|
156
|
+
without output. Reports add the key `source` (`env`/`file`), never the path.
|
|
157
|
+
- stdin/stdout support in the CLI (#8): `-` as INPUT for `inspect`, `plan`, `sanitize` and
|
|
158
|
+
`rescan` (requires `--format`), and `sanitize --output -`. stdin is spooled to a private,
|
|
159
|
+
size-capped temporary workspace that is always removed; stdout receives data only after every
|
|
160
|
+
check passed, with the summary on stderr. A closed pipe exits 5 (`stdout_broken_pipe`).
|
|
161
|
+
`--report -` is refused (it would previously have created a file named `-`).
|
|
162
|
+
|
|
163
|
+
### Changed
|
|
164
|
+
|
|
165
|
+
- Run reports list a `source` for each key (`env` or `file`).
|
|
166
|
+
- The Python API still rejects a directory input (`input_is_directory`); the message now points
|
|
167
|
+
to the CLI, which supports directory runs.
|
|
168
|
+
|
|
169
|
+
## [0.1.1] - 2026-10-29
|
|
170
|
+
|
|
171
|
+
Patch release: corrects the declared minimum dependency versions and hardens CI. No change
|
|
172
|
+
to detection, policy or transform behaviour.
|
|
173
|
+
|
|
174
|
+
### Fixed
|
|
175
|
+
|
|
176
|
+
- Runtime dependency floors were not actually supported: with `typer` 0.12–0.18 and a current
|
|
177
|
+
`click`, most CLI commands failed. The minimum is now `typer>=0.19`, and `PyYAML>=6.0.1`
|
|
178
|
+
(6.0 does not install on current Python). A new `min-deps` CI job runs the suite at the
|
|
179
|
+
declared lower bounds (`ci/constraints-min.txt`) so floors stay tested (#5).
|
|
180
|
+
|
|
181
|
+
### Security
|
|
182
|
+
|
|
183
|
+
- CI actions are pinned to full commit SHAs (`actions/checkout` v7.0.1,
|
|
184
|
+
`actions/setup-python` v7.1.0) and checkout no longer persists the GitHub credential; a
|
|
185
|
+
tooling test enforces both (#5).
|
|
186
|
+
- Dependabot only raises dependency lower bounds when a new release falls outside the declared
|
|
187
|
+
range, groups Actions updates, and never updates `ci/constraints-min.txt`.
|
|
188
|
+
|
|
189
|
+
## [0.1.0] - 2026-10-28
|
|
190
|
+
|
|
191
|
+
First release (still alpha quality: pre-1.0, interfaces may change). Same software as 0.1.0a1,
|
|
192
|
+
plus a configured security contact. Policy templates still need review for each real workflow
|
|
193
|
+
(#3); a successful run is never proof that output contains no sensitive data.
|
|
194
|
+
|
|
195
|
+
### Added
|
|
196
|
+
|
|
197
|
+
- Security contact in `SECURITY.md` (email), target response times, report scope and
|
|
198
|
+
supported versions (#2).
|
|
199
|
+
|
|
200
|
+
## [0.1.0a1] - 2026-10-28
|
|
201
|
+
|
|
202
|
+
Pre-release (alpha). Licensed under Apache-2.0. Not a final release: the security contact in
|
|
203
|
+
`SECURITY.md` is still a placeholder (#2), and policy templates need review for real workflows
|
|
204
|
+
(#3).
|
|
205
|
+
|
|
206
|
+
### Added
|
|
207
|
+
|
|
208
|
+
- Apache-2.0 license (`LICENSE`, `NOTICE`, package metadata).
|
|
209
|
+
- Repository workflow: `scripts/git_safety_check.py` (protected-branch, forbidden-path, size and
|
|
210
|
+
secret-pattern checks with a hashed allowlist), `scripts/check_commit_msg.py` (Conventional
|
|
211
|
+
Commits), pre-commit `git-safety`/`commit-msg` hooks, a `repo-safety` CI job with PR-title
|
|
212
|
+
check, PR template, issue forms, Dependabot, and the `/git-workflow` Claude Code skill.
|
|
213
|
+
- `ciphergate` CLI (first implementation, #12): `init`, `validate-policy`, `inspect`, `plan`, `sanitize --apply`, `rescan`,
|
|
214
|
+
`explain`, `--version`; documented exit codes 0–8 and 130.
|
|
215
|
+
- Python API: `load_policy`, `validate_policy`, `inspect_file`, `plan_file`, `sanitize_file`,
|
|
216
|
+
`rescan_file`.
|
|
217
|
+
- Readers/writers for CSV, JSON, JSONL/NDJSON and text/log with size, line, depth and findings
|
|
218
|
+
limits; strict UTF-8 by default.
|
|
219
|
+
- Detectors: field names, policy classifications, email, phone, IPv4/IPv6, Luhn cards, dates/DOB,
|
|
220
|
+
secrets (incl. multi-line PEM blocks), internal hosts, custom regex with safety heuristics.
|
|
221
|
+
- Policy schema v1 (pydantic, unknown keys rejected), safe YAML loader, computed precedence
|
|
222
|
+
levels, conflict rejection, credential hard constraints, risky-allow acknowledgement,
|
|
223
|
+
environment/destination context with pinning and explicit overrides, run-level guardrails
|
|
224
|
+
(PRD -> non-production, strict + rescan for external/unknown/prd targets), reviewed transfer
|
|
225
|
+
approvals.
|
|
226
|
+
- Actions: allow, redact, replace, pseudonymize (HMAC-SHA-256, transform version `pz1`),
|
|
227
|
+
generalize, date_shift, drop_field, drop_record, block, review. `tokenize` rejected.
|
|
228
|
+
- Two-pass sanitize with plan/apply consistency check, residual rescan gate, input-change
|
|
229
|
+
detection and atomic, no-overwrite publishing.
|
|
230
|
+
- Privacy-safe JSON (`ciphergate.report/v1`) and text reports.
|
|
231
|
+
- Policy templates: dev_local, stg_test, prd_external_ai, developer_logs, test_dataset,
|
|
232
|
+
external_ai, healthcare_template, financial_template, local_debug, multi_environment.
|
|
233
|
+
- Synthetic examples with expected outputs; docs; CI workflow; Claude Code skills, subagents and
|
|
234
|
+
hooks for development.
|
|
235
|
+
|
|
236
|
+
### Changed
|
|
237
|
+
|
|
238
|
+
- CI tests Linux (Python 3.11-3.13) and Windows (3.12); macOS was dropped because hosted
|
|
239
|
+
runners could not be acquired (#21).
|
|
240
|
+
|
|
241
|
+
### Security fixes before first release (from an independent review)
|
|
242
|
+
|
|
243
|
+
- CSV header cells are now scanned, transformed (allow/drop_field/block/review), rescanned and
|
|
244
|
+
hidden in reports when they produce a finding; previously the header was published unscanned.
|
|
245
|
+
- The rescan gate can no longer be emptied: `fail_on_categories: []` is rejected,
|
|
246
|
+
`credential.secret` always gates, and untrusted destinations gate on every high-risk category.
|
|
247
|
+
- A missing destination is treated as untrusted by run-level gates (strict + rescan required).
|
|
248
|
+
- `secret_pattern`/`field_name` cannot be disabled for strict/untrusted/transfer policies or runs.
|
|
249
|
+
- JSON keys must be scanned for untrusted destinations; all templates set `scan_json_keys: true`.
|
|
250
|
+
- Custom categories in high-risk families are high-risk; external/unknown target environments
|
|
251
|
+
count as untrusted for `allow` acknowledgement.
|
|
252
|
+
- Transfer approvals must name every supplied context dimension; future `approved_on` rejected.
|
|
253
|
+
- Temp-file cleanup failures are logged; a report-write failure after publishing says so.
|
|
254
|
+
- `developer_logs` keeps identifiers for internal destinations only for DEV/STG-origin data.
|
|
255
|
+
- CSV writer quotes rows containing a lone CR/LF (previously such a value could be corrupted).
|
|
256
|
+
|
|
257
|
+
### Known limitations
|
|
258
|
+
|
|
259
|
+
See `docs/limitations.md`. Deferred: optional NER/Presidio detectors, stdin/stdout streaming,
|
|
260
|
+
directory processing, structured log parsers, key files, reversible token vault, lossy decoding.
|
|
261
|
+
|
|
262
|
+
[Unreleased]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.7.0...HEAD
|
|
263
|
+
[0.7.0]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.6.1...v0.7.0
|
|
264
|
+
[0.6.1]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.6.0...v0.6.1
|
|
265
|
+
[0.6.0]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.5.0...v0.6.0
|
|
266
|
+
[0.5.0]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.4.0...v0.5.0
|
|
267
|
+
[0.4.0]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.3.0...v0.4.0
|
|
268
|
+
[0.3.0]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.2.0...v0.3.0
|
|
269
|
+
[0.2.0]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.1.1...v0.2.0
|
|
270
|
+
[0.1.1]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.1.0...v0.1.1
|
|
271
|
+
[0.1.0]: https://github.com/aashishkumar-tech/ciphergate/compare/v0.1.0a1...v0.1.0
|
|
272
|
+
[0.1.0a1]: https://github.com/aashishkumar-tech/ciphergate/releases/tag/v0.1.0a1
|
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
202
|
+
|