Merge pull request #472 from cccs-rs/master

Simplify fetching of YARA rules for MACO extractors

.gitignore

@@ -1,2 +1,182 @@
-test.py
-.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# Ignore YARA rules that were downloaded from the core for MACO extractors
+*/parsers/yara/*.yar

modules/parsers/MACO/AgentTesla.py

@@ -1,8 +1,7 @@
-import os
-
-from cape_parsers.CAPE.community.AgentTesla import extract_config
 from maco.extractor import Extractor
 from maco.model import ExtractorModel as MACOModel
+from cape_parsers.CAPE.community.AgentTesla import extract_config
+from modules.parsers.utils import get_YARA_rule
 
 
 def convert_to_MACO(raw_config: dict) -> MACOModel:
@@ -15,7 +14,11 @@ def convert_to_MACO(raw_config: dict) -> MACOModel:
 
     parsed_result = MACOModel(family="AgentTesla", other=raw_config)
     if protocol == "Telegram":
-        parsed_result.http.append(MACOModel.Http(uri=raw_config["C2"], password=raw_config["Password"], usage="c2"))
+        parsed_result.http.append(
+            MACOModel.Http(
+                uri=raw_config["C2"], password=raw_config["Password"], usage="c2"
+            )
+        )
 
     elif protocol in ["HTTP(S)", "Discord"]:
         parsed_result.http.append(MACOModel.Http(uri=raw_config["C2"], usage="c2"))
@@ -43,7 +46,9 @@ def convert_to_MACO(raw_config: dict) -> MACOModel:
         parsed_result.smtp.append(MACOModel.SMTP(**smtp))
 
     if "Persistence_Filename" in raw_config:
-        parsed_result.paths.append(MACOModel.Path(path=raw_config["Persistence_Filename"], usage="storage"))
+        parsed_result.paths.append(
+            MACOModel.Path(path=raw_config["Persistence_Filename"], usage="storage")
+        )
 
     if "ExternalIPCheckServices" in raw_config:
         for service in raw_config["ExternalIPCheckServices"]:
@@ -57,7 +62,7 @@ class AgentTesla(Extractor):
     family = "AgentTesla"
     last_modified = "2024-10-20"
     sharing = "TLP:CLEAR"
-    yara_rule = open(os.path.join(os.path.dirname(__file__).split("/modules", 1)[0], f"data/yara/CAPE/{family}.yar")).read()
+    yara_rule = get_YARA_rule(family)
 
     def run(self, stream, matches):
         return convert_to_MACO(extract_config(stream.read()))

modules/parsers/MACO/AsyncRAT.py

@@ -1,8 +1,9 @@
 import os
 
-from cape_parsers.CAPE.community.AsyncRAT import extract_config
 from maco.extractor import Extractor
 from maco.model import ExtractorModel as MACOModel
+from cape_parsers.CAPE.community.AsyncRAT import extract_config
+from modules.parsers.utils import get_YARA_rule
 
 
 def convert_to_MACO(raw_config: dict) -> MACOModel:
@@ -25,16 +26,29 @@ def convert_to_MACO(raw_config: dict) -> MACOModel:
 
     # Installation Path
     if raw_config.get("Folder"):
-        parsed_result.paths.append(MACOModel.Path(path=os.path.join(raw_config["Folder"], raw_config["Filename"]), usage="install"))
+        parsed_result.paths.append(
+            MACOModel.Path(
+                path=os.path.join(raw_config["Folder"], raw_config["Filename"]),
+                usage="install",
+            )
+        )
 
     # C2s
     for i in range(len(raw_config.get("C2s", []))):
-        parsed_result.http.append(MACOModel.Http(hostname=raw_config["C2s"][i], port=int(raw_config["Ports"][i]), usage="c2"))
+        parsed_result.http.append(
+            MACOModel.Http(
+                hostname=raw_config["C2s"][i],
+                port=int(raw_config["Ports"][i]),
+                usage="c2",
+            )
+        )
     # Pastebin
     if raw_config.get("Pastebin") not in ["null", None]:
         # TODO: Is it used to download the C2 information if not embedded?
         # Ref: https://www.netskope.com/blog/asyncrat-using-fully-undetected-downloader
-        parsed_result.http.append(MACOModel.Http(uri=raw_config["Pastebin"], usage="download"))
+        parsed_result.http.append(
+            MACOModel.Http(uri=raw_config["Pastebin"], usage="download")
+        )
 
     return parsed_result
 
@@ -44,7 +58,7 @@ class AsyncRAT(Extractor):
     family = "AsyncRAT"
     last_modified = "2024-10-26"
     sharing = "TLP:CLEAR"
-    yara_rule = open(os.path.join(os.path.dirname(__file__).split("/modules", 1)[0], f"data/yara/CAPE/{family}.yar")).read()
+    yara_rule = get_YARA_rule(family)
 
     def run(self, stream, matches):
         return convert_to_MACO(extract_config(stream.read()))

modules/parsers/MACO/AuroraStealer.py

@@ -1,8 +1,7 @@
-import os
-
-from cape_parsers.CAPE.community.AuroraStealer import extract_config
 from maco.extractor import Extractor
 from maco.model import ExtractorModel as MACOModel
+from cape_parsers.CAPE.community.AuroraStealer import extract_config
+from modules.parsers.utils import get_YARA_rule
 
 
 def convert_to_MACO(raw_config: dict):
@@ -22,7 +21,7 @@ class AuroraStealer(Extractor):
     family = "AuroraStealer"
     last_modified = "2024-10-26"
     sharing = "TLP:CLEAR"
-    yara_rule = open(os.path.join(os.path.dirname(__file__).split("/modules", 1)[0], f"data/yara/CAPE/{family}.yar")).read()
+    yara_rule = get_YARA_rule(family)
 
     def run(self, stream, matches):
         return convert_to_MACO(extract_config(stream.read()))

modules/parsers/MACO/Azorult.py

@@ -1,21 +1,26 @@
-from cape_parsers.CAPE.core.Azorult import extract_config, rule_source
 from maco.extractor import Extractor
 from maco.model import ExtractorModel as MACOModel
+from cape_parsers.CAPE.core.Azorult import extract_config, rule_source
+from modules.parsers.utils import get_YARA_rule
 
 
 def convert_to_MACO(raw_config: dict):
     if not raw_config:
         return None
 
-    return MACOModel(family="Azorult", http=[MACOModel.Http(hostname=raw_config["address"])], other=raw_config)
+    return MACOModel(
+        family="Azorult",
+        http=[MACOModel.Http(hostname=raw_config["address"])],
+        other=raw_config,
+    )
 
 
 class Azorult(Extractor):
     author = "kevoreilly"
     family = "Azorult"
     last_modified = "2024-10-26"
     sharing = "TLP:CLEAR"
-    yara_rule = rule_source
+    yara_rule = get_YARA_rule(family) or rule_source
 
     def run(self, stream, matches):
         return convert_to_MACO(extract_config(stream.read()))

modules/parsers/MACO/BackOffLoader.py

@@ -1,6 +1,7 @@
-from cape_parsers.CAPE.community.BackOffLoader import extract_config
 from maco.extractor import Extractor
 from maco.model import ExtractorModel as MACOModel
+from cape_parsers.CAPE.community.BackOffLoader import extract_config
+from modules.parsers.utils import get_YARA_rule
 
 
 def convert_to_MACO(raw_config: dict):
@@ -14,7 +15,9 @@ def convert_to_MACO(raw_config: dict):
 
     # Encryption details
     parsed_result.encryption.append(
-        MACOModel.Encryption(algorithm="rc4", key=raw_config["EncryptionKey"], seed=raw_config["RC4Seed"])
+        MACOModel.Encryption(
+            algorithm="rc4", key=raw_config["EncryptionKey"], seed=raw_config["RC4Seed"]
+        )
     )
     for url in raw_config["URLs"]:
         parsed_result.http.append(MACOModel.Http(url=url))
@@ -27,6 +30,7 @@ class BackOffLoader(Extractor):
     family = "BackOffLoader"
     last_modified = "2024-10-26"
     sharing = "TLP:CLEAR"
+    yara_rule = get_YARA_rule(family)
 
     def run(self, stream, matches):
         return convert_to_MACO(extract_config(stream.read()))

modules/parsers/MACO/BackOffPOS.py

@@ -1,6 +1,7 @@
-from cape_parsers.CAPE.community.BackOffPOS import extract_config
 from maco.extractor import Extractor
 from maco.model import ExtractorModel as MACOModel
+from cape_parsers.CAPE.community.BackOffPOS import extract_config
+from modules.parsers.utils import get_YARA_rule
 
 
 def convert_to_MACO(raw_config: dict):
@@ -14,7 +15,9 @@ def convert_to_MACO(raw_config: dict):
 
     # Encryption details
     parsed_result.encryption.append(
-        MACOModel.Encryption(algorithm="rc4", key=raw_config["EncryptionKey"], seed=raw_config["RC4Seed"])
+        MACOModel.Encryption(
+            algorithm="rc4", key=raw_config["EncryptionKey"], seed=raw_config["RC4Seed"]
+        )
     )
     for url in raw_config["URLs"]:
         parsed_result.http.append(MACOModel.Http(url=url))
@@ -27,6 +30,7 @@ class BackOffPOS(Extractor):
     family = "BackOffPOS"
     last_modified = "2024-10-26"
     sharing = "TLP:CLEAR"
+    yara_rule = get_YARA_rule(family)
 
     def run(self, stream, matches):
         return convert_to_MACO(extract_config(stream.read()))