kodon 0.0.1__tar.gz

kodon-0.0.1/.gitignore

@@ -0,0 +1,32 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+build/
+dist/
+.eggs/
+
+# Environments
+.venv/
+venv/
+
+# Tooling
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.coverage
+htmlcov/
+
+# Editors / OS
+.idea/
+.vscode/
+*.swp
+.DS_Store
+
+# Scan output and collected telemetry (never commit)
+scan-results/
+collected/
+
+# Local secrets and private notes (never commit)
+.env
+*.private

kodon-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Mark Peters
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

kodon-0.0.1/PKG-INFO

@@ -0,0 +1,291 @@
+Metadata-Version: 2.5
+Name: kodon
+Version: 0.0.1
+Summary: Detection-as-code: Sigma rules compiled to Splunk SPL, Sentinel KQL and DuckDB SQL, replay-tested on synthetic telemetry.
+Project-URL: Homepage, https://github.com/markrpeters/kodon
+Project-URL: Issues, https://github.com/markrpeters/kodon/issues
+Author: Mark Peters
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: attack,detection-as-code,detection-engineering,dfir,duckdb,kql,sentinel,sigma,splunk
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Information Technology
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Security
+Requires-Python: >=3.10
+Requires-Dist: duckdb>=1.1
+Requires-Dist: pydantic<3,>=2
+Requires-Dist: pysigma-backend-kusto<2,>=1.0
+Requires-Dist: pysigma-backend-splunk<3,>=2.1
+Requires-Dist: pysigma-backend-sqlite<2,>=1.2
+Requires-Dist: pysigma<2,>=1.5
+Requires-Dist: pyyaml>=6
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == 'dev'
+Requires-Dist: ruff>=0.5; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# kodon
+
+[![ci](https://github.com/markrpeters/kodon/actions/workflows/ci.yml/badge.svg)](https://github.com/markrpeters/kodon/actions/workflows/ci.yml)
+
+Detections should be files in a repo, not rules in a console: version-controlled,
+reviewed, tested against data that must trigger them and data that must not,
+validated in CI, mapped to ATT&CK with the gaps listed, and deployed from the
+pipeline rather than by hand. kodon is that lifecycle. Rules are written in
+Sigma (vendor-neutral), compiled to Splunk SPL, Microsoft Sentinel KQL and
+DuckDB SQL with pySigma, and replay-tested against synthetic telemetry in
+DuckDB. pySigma does the compiling; what kodon adds is the contract around
+each rule (required metadata, generated must-hit and must-not-hit samples,
+replay, a declared ATT&CK scope) and the CI that enforces it.
+
+Ten rules ship today, each built around a pattern the author has had to
+detect in practice. Each carries a must-hit and a must-not-hit
+sample set, an ATT&CK mapping, and a `do_not_alert_when` block that says when
+the rule should run as a hunt query rather than page as an alert. Status: 0.0.1, alpha, a personal project.
+Requires Python 3.10 or newer; the test suite runs offline in about a second.
+
+## 30-second demo
+
+```bash
+git clone https://github.com/markrpeters/kodon && cd kodon
+python -m venv .venv && . .venv/bin/activate
+pip install -e '.[dev]'
+kodon demo
+```
+
+The demo generates the seeded samples into a temporary directory, validates
+every rule against the metadata contract, compiles all of them to the three
+targets, replays the DuckDB SQL over the samples, and prints the coverage
+matrix. A rule looks like this (excerpt of
+`rules/windows/nltest_domain_trust_enum_workstation.yml`):
+
+```yaml
+detection:
+  selection:
+    Image|endswith: '\nltest.exe'
+    CommandLine|contains:
+      - 'domain_trusts'
+      - 'all_trusts'
+      - 'trusted_domains'
+      - 'dclist'
+      - 'dsgetdc'
+  filter_domain_controllers:
+    ComputerName|startswith: 'HOST-DC'
+  filter_admin_tooling:
+    ParentImage|endswith:
+      - '\ServerManager.exe'
+      - '\dsac.exe'
+  condition: selection and not 1 of filter_*
+custom:
+  do_not_alert_when: |
+    The parent is a known management tool or the user is in the directory
+    administrators group and the host is their assigned admin workstation;
+    filter by parent process, not by user name alone, because attackers run as
+    the compromised admin. Treat /dsgetdc on its own as a hunt (scripts use
+    it); /domain_trusts and /all_trusts from a standard user should alert.
+```
+
+And the demo output, with one correlation rule shown in all three languages:
+
+```text
+[1/5] generated seeded samples for 10 rules (57 must-hit rows, 152 must-miss rows)
+[2/5] validated 10 rules against the metadata contract
+[3/5] compiled 10 rules to splunk, kql, duckdb
+
+example, mfa_success_multi_country_window:
+--- splunk
+eventType IN ("user.authentication.auth_via_mfa", "user.session.start") outcome.result="SUCCESS"
+| bin _time span=1h
+| stats dc(client.geographicalContext.country) as value_count by _time actor.alternateId
+| search value_count >= 2
+--- kql
+Okta_CL
+| where (eventType in~ ("user.authentication.auth_via_mfa", "user.session.start")) and ['outcome.result'] =~ "SUCCESS"
+| summarize value_count = dcount(['client.geographicalContext.country']) by bin(TimeGenerated, 1h), ['actor.alternateId']
+| where value_count >= 2
+--- duckdb
+SELECT time_bucket(INTERVAL '3600 seconds', ts) AS bucket, user, COUNT(DISTINCT src_country) AS value_count
+FROM (SELECT * FROM events
+      WHERE (event_type ILIKE 'user.authentication.auth\_via\_mfa' ESCAPE '\'
+             OR event_type ILIKE 'user.session.start' ESCAPE '\')
+        AND outcome ILIKE 'SUCCESS' ESCAPE '\') AS subquery
+GROUP BY 1, user HAVING COUNT(DISTINCT src_country) >= 2
+
+[4/5] replay: compiled DuckDB SQL over the samples
+      (a rule passes when it matches at least one hit row and zero miss rows)
+rule_id                                    hit rows  matched miss rows  matched  result
+xmailer_cli_mailer_anomaly                        3        2         4        0  PASS
+inbox_rule_external_forward                       2        1         4        0  PASS
+mfa_success_multi_country_window                  3        1         6        0  PASS
+...
+kerberos_rc4_tgs_volume_single_host              16        1        41        0  PASS
+
+[5/5] coverage
+ATT&CK coverage: 12/24 in-scope techniques have at least one rule; 12 gaps
+```
+
+The Splunk and KQL output is compiled, not deployed: field names stay Sigma's
+until you pass your own field-mapping pipeline (see *How to compile*), and only
+the DuckDB target is replay-tested.
+
+## The rules
+
+| rule | logsource | technique | kind |
+|---|---|---|---|
+| `identity/mfa_success_multi_country_window` | okta | T1078.004, T1621 | correlation |
+| `identity/inbox_rule_external_forward` | m365 exchange | T1114.003 | event |
+| `identity/oauth_consent_mail_files_scopes_by_user` | azure auditlogs | T1528 | event |
+| `windows/msbuild_masquerade_network_egress` | windows network_connection | T1127.001, T1036.005 | event |
+| `windows/nltest_domain_trust_enum_workstation` | windows process_creation | T1482 | event |
+| `windows/wmi_remote_process_creation` | windows process_creation | T1047 | event |
+| `windows/kerberos_rc4_tgs_volume_single_host` | windows security | T1558.003 | correlation |
+| `network/beacon_fixed_destination_high_count` | zeek conn | T1071.001 | correlation |
+| `network/reverse_shell_conn_shape` | zeek conn | T1571 | event |
+| `email/xmailer_cli_mailer_anomaly` | zeek smtp | T1048.003 | event |
+
+The patterns are well known and several have SigmaHQ cousins; the selections,
+filters, samples and `do_not_alert_when` text here are written from scratch,
+and each rule cites the ATT&CK page for its technique.
+
+## How to add a rule
+
+1. Write `rules/<domain>/<rule_id>.yml` in Sigma. The file stem is the rule id.
+   The Sigma `id` is derived, not invented: `uuid5(NAMESPACE_URL, "kodon:<rule_id>")`
+   written as 32 hex characters (see *Design notes* for why no hyphens).
+   The loader refuses any other value.
+2. Fill the metadata contract. Besides the Sigma fields the loader requires
+   `status`, `level`, `date`, at least one `attack.tNNNN` tag and one
+   `attack.<tactic>` tag, a non-empty `falsepositives` list, and a `custom`
+   block:
+
+   ```yaml
+   custom:
+     data_sources: [what log this needs, precisely]
+     do_not_alert_when: |
+       The judgment call: the conditions under which this stays a hunt.
+     detection_health: {added: 2026-09-18, last_reviewed: 2026-09-18, owner: Mark Peters}
+   ```
+
+   `do_not_alert_when` is mandatory and is the most important field in the
+   file. A rule that cannot say when it should not fire is not finished.
+3. For a threshold rule, append a Sigma correlation document to the same file
+   (`event_count` or `value_count`, with `group-by` and `timespan`). Give the
+   base rule a `name` and reference it. Three of the shipped rules show this.
+4. Add a generator to `src/kodon/synth.py` under `@generator("<rule_id>")`
+   that returns the must-hit rows and the must-not-hit rows, then run
+   `python scripts/gen_samples.py` to write `tests/samples/<rule_id>/`.
+   Samples are never written by hand; a test regenerates them from the seed
+   and compares byte for byte with the committed files. Put the near-misses in
+   the miss set: the legitimate path, the domain controller, the machine
+   account, the admin consent. Those rows are what the filters are for.
+5. If the technique is new, add it to `coverage/attack_scope.yml`.
+6. `pytest`. A rule without both sample sets, or with a miss that matches,
+   does not merge.
+
+## How to compile
+
+```bash
+kodon compile --target splunk
+kodon compile --target kql --rule wmi_remote_process_creation
+kodon compile --target duckdb
+```
+
+Field names in the Splunk and KQL output are the Sigma taxonomy names
+(`Image`, `CommandLine`, `id.orig_h`). Mapping them onto a deployment's real
+columns is a pySigma processing pipeline the deployment owns; pass it as
+`pipeline=` to `kodon.compile_rule`. `pipelines/synthetic_canonical.yml` is
+the public example of that file: it maps the same names onto the synthetic
+schema the tests run against. A deployment ships its own copy for its own
+schema and nothing else changes. `pipelines/kql_tables.yml` picks the Sentinel
+table per logsource.
+
+## How to test
+
+```bash
+pytest          # validate, compile, replay, coverage; offline
+kodon test      # the replay table only
+kodon validate  # the metadata contract only
+```
+
+Replay is the gate: each rule's DuckDB SQL runs over
+`tests/samples/<rule_id>/hit.jsonl` and must match at least one row, then over
+`miss.jsonl` and must match none. It is a regression test against synthetic
+rows, not proof against production telemetry; that proof comes from the
+deployment's own data once the rule is compiled for it. Hits come back as
+`DetectionHit` records (rule id, technique, severity, the matched row or the
+matched aggregate), the same contract a downstream consumer receives from
+`kodon.replay`.
+
+## Coverage report
+
+```bash
+kodon coverage            # text matrix, gaps marked
+kodon coverage --json     # the CoverageReport contract
+```
+
+Gaps are computed against the declared scope in `coverage/attack_scope.yml`,
+not against all of ATT&CK. The scope is a choice, so the percentage is too; a
+matrix that is red everywhere says nothing, and a scope says what the rule
+set was meant to cover. The gaps are the work list. CI uploads the report as
+an artifact on every push.
+
+## Design notes
+
+**Sigma ids without hyphens.** The data-hygiene scanner that gates every
+commit and CI run (`scripts/ip_scan.sh`) flags hyphenated UUIDs, and exempting
+the rules directory would leave the files most likely to carry a copied
+identifier unscanned. Python's `uuid.UUID` and pySigma both accept the 32-hex
+form, and ids are derived from the rule id so they are reproducible.
+
+**Correlation windows are fixed buckets.** All three targets aggregate into
+fixed time buckets (`bin _time span=`, `bin(TimeGenerated, …)`,
+`time_bucket(INTERVAL …)`). A burst that straddles a bucket boundary can be
+missed; a sliding window is a roadmap item, not something to hide.
+
+**KQL correlations are kodon's.** pySigma's Kusto backend (1.0) does not emit
+correlation rules, so kodon appends the `summarize` clause itself, using the
+same fields and window the other two targets use. kodon's DuckDB backend is a
+thin subclass of the maintained pySigma SQLite backend: `ILIKE` because Sigma
+matching is case-insensitive and DuckDB's `LIKE` is not, `regexp_matches()`
+because DuckDB has no `REGEXP`, and the time bucketing above. Underscores in
+values are escaped (`auth\_via\_mfa`) because `_` is a `LIKE` wildcard.
+
+**Synthetic address plan.** Samples use the RFC 5737 documentation ranges:
+192.0.2.0/24 plays the inside network, 198.51.100.0/24 and 203.0.113.0/24 the
+outside. Domains are RFC 2606 (`example.com` is the organisation). Hosts are
+HOST-A, HOST-B, HOST-C and the domain controller HOST-DC1. Where a rule needs
+an "internal" range or a naming prefix, it uses these, with a comment that a
+deployment substitutes its own.
+
+**One-way dependency.** kodon is also a library, used by a separate private
+project of the author's that passes its own field-mapping pipeline and
+consumes the `DetectionHit` records. Nothing private is referenced, imported
+or tested here; the scanner and its self-test run in CI and as a pre-commit
+hook to keep it that way.
+
+## Roadmap
+
+- Sliding-window correlations, and interval-variance scoring for the beacon
+  rule (periodicity, not just count).
+- More rules, generalised from hunt queries in the downstream project.
+- Optional Defender XDR and Sentinel ASIM field mapping for the Windows
+  categories via the pipelines that ship with pysigma-backend-kusto.
+- Deployment: push compiled output to a SIEM from CI. Compile is the
+  deliverable today; deployment is deliberately not.
+
+## Why the name
+
+A codon is the smallest unit of genetic code that encodes one instruction. A
+rule here is one encoded instruction: a Sigma file with its samples and
+metadata, compiled into whichever language the target speaks. The k is a
+spelling swap to stay clear of the Codon compiler.
+
+## License
+
+Apache-2.0. Copyright 2026 Mark Peters ([github.com/markrpeters](https://github.com/markrpeters)).