bbot 2.6.0.6840rc0__py3-none-any.whl → 2.7.2.7424rc0__py3-none-any.whl

bbot/core/helpers/regex.py

@@ -65,7 +65,7 @@ class RegexHelper:
 
         while tasks:  # While there are tasks pending
             # Wait for the first task to complete
-            done, pending = await asyncio.wait(tasks, return_when=asyncio.FIRST_COMPLETED)
+            done, _ = await asyncio.wait(tasks, return_when=asyncio.FIRST_COMPLETED)
 
             for task in done:
                 result = task.result()

bbot/core/helpers/regexes.py

@@ -23,13 +23,28 @@ num_regex = re.compile(r"\d+")
 _ipv4_regex = r"(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)(?:\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)){3}"
 ipv4_regex = re.compile(_ipv4_regex, re.I)
 
-# IPv6 is complicated, so we have accommodate alternative patterns,
-# :(:[A-F0-9]{1,4}){1,7} == ::1, ::ffff:1
-# ([A-F0-9]{1,4}:){1,7}: == 2001::, 2001:db8::, 2001:db8:0:1:2:3::
-# ([A-F0-9]{1,4}:){1,6}:([A-F0-9]{1,4}) == 2001::1, 2001:db8::1, 2001:db8:0:1:2:3::1
-# ([A-F0-9]{1,4}:){7,7}([A-F0-9]{1,4}) == 1:1:1:1:1:1:1:1, ffff:ffff:ffff:ffff:ffff:ffff:ffff:ffff
-
-_ipv6_regex = r"(:(:[A-F0-9]{1,4}){1,7}|([A-F0-9]{1,4}:){1,7}:|([A-F0-9]{1,4}:){1,6}:([A-F0-9]{1,4})|([A-F0-9]{1,4}:){7,7}([A-F0-9]{1,4}))"
+# IPv6 regex breakdown:
+#
+# (?:                            # —— address body ——
+# We have to individually account for all possible variations of: "N left hextets :: M right hextets" with N+M ≤ 8 or fully expanded 8 hextets.
+#   (?:[A-F0-9]{1,4}:){7}[A-F0-9]{1,4}        # 8 hextets, no compression.
+# | (?:[A-F0-9]{1,4}:){1,7}:                  # 1–7 left, then "::" (0 right).
+# | (?:[A-F0-9]{1,4}:){1,6}:[A-F0-9]{1,4}     # 1–6 left, "::", 1 right.
+# | (?:[A-F0-9]{1,4}:){1,5}(?::[A-F0-9]{1,4}){1,2}  # 1–5 left, "::", 1–2 right.
+# | (?:[A-F0-9]{1,4}:){1,4}(?::[A-F0-9]{1,4}){1,3}  # 1–4 left, "::", 1–3 right.
+# | (?:[A-F0-9]{1,4}:){1,3}(?::[A-F0-9]{1,4}){1,4}  # 1–3 left, "::", 1–4 right.
+# | (?:[A-F0-9]{1,4}:){1,2}(?::[A-F0-9]{1,4}){1,5}  # 1–2 left, "::", 1–5 right.
+# | [A-F0-9]{1,4}:(?::[A-F0-9]{1,4}){1,6}           # 1 left,    "::", 1–6 right.
+# | :(?::[A-F0-9]{1,4}){1,7}                        # 0 left,    "::", 1–7 right.
+# | ::                                              # all zeros.
+# )
+#
+# Notes:
+# - Does not match IPv4-embedded forms (e.g., ::ffff:192.0.2.1).
+# - Does not match zone IDs (e.g., %eth0).
+# - Pure syntax check; will not validate special ranges.
+
+_ipv6_regex = r"(?:(?:[A-F0-9]{1,4}:){7}[A-F0-9]{1,4}|(?:[A-F0-9]{1,4}:){1,7}:|(?:[A-F0-9]{1,4}:){1,6}:[A-F0-9]{1,4}|(?:[A-F0-9]{1,4}:){1,5}(?::[A-F0-9]{1,4}){1,2}|(?:[A-F0-9]{1,4}:){1,4}(?::[A-F0-9]{1,4}){1,3}|(?:[A-F0-9]{1,4}:){1,3}(?::[A-F0-9]{1,4}){1,4}|(?:[A-F0-9]{1,4}:){1,2}(?::[A-F0-9]{1,4}){1,5}|[A-F0-9]{1,4}:(?::[A-F0-9]{1,4}){1,6}|:(?::[A-F0-9]{1,4}){1,7}|::)"
 ipv6_regex = re.compile(_ipv6_regex, re.I)
 
 _ip_range_regexes = (
@@ -173,7 +188,9 @@ button_tag_regex2 = re.compile(
 )
 tag_attribute_regex = re.compile(r"<[^>]*(?:href|action|src)\s*=\s*[\"\']?(?!mailto:)([^\'\"\>]+)[\"\']?[^>]*>")
 
-valid_netloc = r"[^\s!@#$%^&()=/?\\'\";~`<>]+"
+_invalid_netloc_chars = r"\s!@#$%^&()=/?\\'\";~`<>"
+# first char must not be a colon, even though it's a valid char for a netloc
+valid_netloc = r"[^" + (_invalid_netloc_chars + ":") + r"]{1}[^" + _invalid_netloc_chars + "]*"
 
 _split_host_port_regex = r"(?:(?P<scheme>[a-z0-9]{1,20})://)?(?:[^?]*@)?(?P<netloc>" + valid_netloc + ")"
 split_host_port_regex = re.compile(_split_host_port_regex, re.I)

bbot/core/helpers/web/web.py

@@ -267,7 +267,8 @@ class WebHelper(EngineClient):
         if not path:
             raise WordlistError(f"Invalid wordlist: {path}")
         if "cache_hrs" not in kwargs:
-            kwargs["cache_hrs"] = 720
+            # 4320 hrs = 180 days = 6 months
+            kwargs["cache_hrs"] = 4320
         if self.parent_helper.is_url(path):
             filename = await self.download(str(path), **kwargs)
             if filename is None:

bbot/core/modules.py

@@ -56,7 +56,6 @@ class ModuleLoader:
         self._shared_deps = dict(SHARED_DEPS)
 
         self.__preloaded = {}
-        self._modules = {}
         self._configs = {}
         self.flag_choices = set()
         self.all_module_choices = set()
@@ -165,8 +164,10 @@ class ModuleLoader:
                         if module_dir.name in ("output", "internal"):
                             module_type = str(module_dir.name)
 
+                        disable_auto_module_deps = preloaded.get("disable_auto_module_deps", False)
+
                         # derive module dependencies from watched event types (only for scan modules)
-                        if module_type == "scan":
+                        if module_type == "scan" and not disable_auto_module_deps:
                             for event_type in preloaded["watched_events"]:
                                 if event_type in self.default_module_deps:
                                     deps_modules = set(preloaded.get("deps", {}).get("modules", []))
@@ -329,6 +330,7 @@ class ModuleLoader:
         ansible_tasks = []
         config = {}
         options_desc = {}
+        disable_auto_module_deps = False
         python_code = open(module_file).read()
         # take a hash of the code so we can keep track of when it changes
         module_hash = sha1(python_code).hexdigest()
@@ -353,8 +355,11 @@ class ModuleLoader:
             # look for classes
             if type(root_element) == ast.ClassDef:
                 for class_attr in root_element.body:
+                    if not type(class_attr) == ast.Assign:
+                        continue
+
                     # class attributes that are dictionaries
-                    if type(class_attr) == ast.Assign and type(class_attr.value) == ast.Dict:
+                    if type(class_attr.value) == ast.Dict:
                         # module options
                         if any(target.id == "options" for target in class_attr.targets):
                             config.update(ast.literal_eval(class_attr.value))
@@ -366,7 +371,7 @@ class ModuleLoader:
                             meta = ast.literal_eval(class_attr.value)
 
                     # class attributes that are lists
-                    if type(class_attr) == ast.Assign and type(class_attr.value) == ast.List:
+                    if type(class_attr.value) == ast.List:
                         # flags
                         if any(target.id == "flags" for target in class_attr.targets):
                             for flag in class_attr.value.elts:
@@ -415,6 +420,12 @@ class ModuleLoader:
                                 if type(dep_common.value) == str:
                                     deps_common.append(dep_common.value)
 
+                    # class attributes that are booleans
+                    if type(class_attr.value) == ast.Constant:
+                        if any(target.id == "_disable_auto_module_deps" for target in class_attr.targets):
+                            if type(class_attr.value.value) == bool:
+                                disable_auto_module_deps = class_attr.value.value
+
         for task in ansible_tasks:
             if "become" not in task:
                 task["become"] = False
@@ -441,6 +452,7 @@ class ModuleLoader:
                 "common": deps_common,
             },
             "sudo": len(deps_apt) > 0,
+            "disable_auto_module_deps": disable_auto_module_deps,
         }
         ansible_task_list = list(ansible_tasks)
         for dep_common in deps_common:
@@ -461,9 +473,13 @@ class ModuleLoader:
     def load_modules(self, module_names):
         modules = {}
         for module_name in module_names:
-            module = self.load_module(module_name)
+            try:
+                module = self.load_module(module_name)
+            except ModuleNotFoundError as e:
+                raise BBOTError(
+                    f"Error loading module {module_name}: {e}. You may have leftover artifacts from an older version of BBOT. Try deleting/renaming your '~/.bbot' directory."
+                ) from e
             modules[module_name] = module
-            self._modules[module_name] = module
         return modules
 
     def load_module(self, module_name):
@@ -512,60 +528,6 @@ class ModuleLoader:
                         # then we have a module
                         return value
 
-    def recommend_dependencies(self, modules):
-        """
-        Returns a dictionary containing missing dependencies and their suggested resolutions
-
-        Needs work. For this we should probably be building a dependency graph
-        """
-        resolve_choices = {}
-        # step 1: build a dictionary containing event types and their associated modules
-        # {"IP_ADDRESS": set("masscan", "ipneighbor", ...)}
-        watched = {}
-        produced = {}
-        for modname in modules:
-            preloaded = self._preloaded.get(modname)
-            if preloaded:
-                for event_type in preloaded.get("watched_events", []):
-                    self.add_or_create(watched, event_type, modname)
-                for event_type in preloaded.get("produced_events", []):
-                    self.add_or_create(produced, event_type, modname)
-        watched_all = {}
-        produced_all = {}
-        for modname, preloaded in self.preloaded().items():
-            if preloaded:
-                for event_type in preloaded.get("watched_events", []):
-                    self.add_or_create(watched_all, event_type, modname)
-                for event_type in preloaded.get("produced_events", []):
-                    self.add_or_create(produced_all, event_type, modname)
-
-        # step 2: check to see if there are missing dependencies
-        for modname in modules:
-            preloaded = self._preloaded.get(modname)
-            module_type = preloaded.get("type", "unknown")
-            if module_type != "scan":
-                continue
-            watched_events = preloaded.get("watched_events", [])
-            missing_deps = {e: not self.check_dependency(e, modname, produced) for e in watched_events}
-            if all(missing_deps.values()):
-                for event_type in watched_events:
-                    if event_type == "SCAN":
-                        continue
-                    choices = produced_all.get(event_type, [])
-                    choices = set(choices)
-                    with suppress(KeyError):
-                        choices.remove(modname)
-                    if event_type not in resolve_choices:
-                        resolve_choices[event_type] = {}
-                    deps = resolve_choices[event_type]
-                    self.add_or_create(deps, "required_by", modname)
-                    for c in choices:
-                        choice_type = self._preloaded.get(c, {}).get("type", "unknown")
-                        if choice_type == "scan":
-                            self.add_or_create(deps, "recommended", c)
-
-        return resolve_choices
-
     def check_dependency(self, event_type, modname, produced):
         if event_type not in produced:
             return False

bbot/defaults.yml

@@ -187,8 +187,10 @@ url_extension_blacklist:
   - mov
   - flv
   - webm
-# Distribute URLs with these extensions only to httpx (these are omitted from output)
-url_extension_httpx_only:
+
+# URLs with these extensions are not distributed to modules unless the module opts in via `accept_url_special = True`
+# They are also excluded from output. If you want to see them in output, remove them from this list.
+url_extension_special:
   - js
 
 # These url extensions are almost always static, so we exclude them from modules that fuzz things

bbot/modules/apkpure.py

@@ -6,7 +6,7 @@ from bbot.modules.base import BaseModule
 class apkpure(BaseModule):
     watched_events = ["MOBILE_APP"]
     produced_events = ["FILESYSTEM"]
-    flags = ["passive", "safe", "code-enum"]
+    flags = ["passive", "safe", "code-enum", "download"]
     meta = {
         "description": "Download android applications from apkpure.com",
         "created_date": "2024-10-11",

bbot/modules/baddns.py

@@ -22,7 +22,7 @@ class baddns(BaseModule):
         "enabled_submodules": "A list of submodules to enable. Empty list (default) enables CNAME, TXT and MX Only",
     }
     module_threads = 8
-    deps_pip = ["baddns~=1.9.130"]
+    deps_pip = ["baddns~=1.12.294"]
 
     def select_modules(self):
         selected_submodules = []

bbot/modules/baddns_direct.py

@@ -19,7 +19,7 @@ class baddns_direct(BaseModule):
         "custom_nameservers": "Force BadDNS to use a list of custom nameservers",
     }
     module_threads = 8
-    deps_pip = ["baddns~=1.9.130"]
+    deps_pip = ["baddns~=1.12.294"]
 
     scope_distance_modifier = 1
 

bbot/modules/baddns_zone.py

@@ -16,7 +16,7 @@ class baddns_zone(baddns_module):
         "only_high_confidence": "Do not emit low-confidence or generic detections",
     }
     module_threads = 8
-    deps_pip = ["baddns~=1.9.130"]
+    deps_pip = ["baddns~=1.12.294"]
 
     def set_modules(self):
         self.enabled_submodules = ["NSEC", "zonetransfer"]

bbot/modules/badsecrets.py

@@ -17,7 +17,7 @@ class badsecrets(BaseModule):
     options_desc = {
         "custom_secrets": "Include custom secrets loaded from a local file",
     }
-    deps_pip = ["badsecrets~=0.9.29"]
+    deps_pip = ["badsecrets~=0.13.47"]
 
     async def setup(self):
         self.custom_secrets = None

bbot/modules/base.py

@@ -4,9 +4,10 @@ import traceback
 from sys import exc_info
 from contextlib import suppress
 
-from ..errors import ValidationError
 from ..core.helpers.misc import get_size  # noqa
+from ..errors import ValidationError, WebError
 from ..core.helpers.async_helpers import TaskCounter, ShuffleQueue
+from ..core.event import is_event
 
 
 class BaseModule:
@@ -53,6 +54,8 @@ class BaseModule:
 
         in_scope_only (bool): Accept only explicitly in-scope events, regardless of the scan's search distance. Default is False.
 
+        accept_url_special (bool): Accept "special" URLs not typically distributed to web modules, e.g. JS URLs. Default is False.
+
         options (Dict): Customizable options for the module, e.g., {"api_key": ""}. Empty dict by default.
 
         options_desc (Dict): Descriptions for options, e.g., {"api_key": "API Key"}. Empty dict by default.
@@ -67,6 +70,8 @@ class BaseModule:
 
         _stats_exclude (bool): Whether to exclude this module from scan statistics. Default is False.
 
+        _disable_auto_module_deps (bool): Whether to disable automatic module dependencies. This is useful e.g. if the module consumes URLs, but you don't want to automatically enable the httpx module. Default is False.
+
         _qsize (int): Outgoing queue size (0 for infinite). Default is 0.
 
         _priority (int): Priority level of the module. Lower values are higher priority. Default is 3.
@@ -97,7 +102,7 @@ class BaseModule:
     scope_distance_modifier = 0
     target_only = False
     in_scope_only = False
-
+    accept_url_special = False
     _module_threads = 1
     _batch_size = 1
 
@@ -110,6 +115,7 @@ class BaseModule:
 
     _preserve_graph = False
     _stats_exclude = False
+    _disable_auto_module_deps = False
     _qsize = 1000
     _priority = 3
     _name = "base"
@@ -163,7 +169,6 @@ class BaseModule:
         self._default_handle_batch_timeout = self.scan.config.get(
             "module_handle_batch_timeout", 60 * 60 * 2
         )  # 2 hours
-        self._event_handler_watchdog_task = None
         self._event_handler_watchdog_interval = self.event_handler_timeout / 10
 
         # used for optional "per host" tracking
@@ -211,6 +216,14 @@ class BaseModule:
 
         return True
 
+    async def setup_deps(self):
+        """
+        Similar to setup(), but reserved for installing dependencies not covered by Ansible.
+
+        This should always be used to install static dependencies like AI models, wordlists, etc.
+        """
+        return True
+
     async def handle_event(self, event, **kwargs):
         """Asynchronously handles incoming events that the module is configured to watch.
 
@@ -510,6 +523,12 @@ class BaseModule:
             if (not args) or getattr(args[0], "module", None) is None:
                 kwargs["module"] = self
         try:
+            if args and is_event(args[0]):
+                raise ValidationError(
+                    f"{self.__class__.__name__}.make_event() does not accept an existing event "
+                    f"({type(args[0]).__name__}) as the first argument. "
+                    "Use update_event(event, ...) or emit_event(event, ...) instead."
+                )
             event = self.scan.make_event(*args, **kwargs)
         except ValidationError as e:
             if raise_error:
@@ -518,6 +537,39 @@ class BaseModule:
             return
         return event
 
+    def update_event(self, event, **kwargs):
+        """Update an existing event for the scan.
+
+        This is the counterpart to :meth:`make_event` for modifying an existing
+        :class:`bbot.core.event.base.BaseEvent` instance.
+
+        Raises a validation error if the update could not be applied, unless
+        ``raise_error`` is set to False.
+
+        Args:
+            event: The event object to update.
+            **kwargs: Keyword arguments to be passed to the scan's update_event method.
+            raise_error (bool, optional): Whether to raise a validation error if the event could not be updated. Defaults to False.
+
+        Returns:
+            Event or None: The updated event, or None if a validation error occurred and raise_error was False.
+
+        Raises:
+            ValidationError: If the event could not be validated and raise_error is True.
+        """
+        raise_error = kwargs.pop("raise_error", False)
+        module = kwargs.pop("module", None)
+        if module is None and getattr(event, "module", None) is None:
+            kwargs["module"] = self
+        try:
+            updated = self.scan.update_event(event, **kwargs)
+        except ValidationError as e:
+            if raise_error:
+                raise
+            self.warning(f"{e}")
+            return
+        return updated
+
     async def emit_event(self, *args, **kwargs):
         """Emit an event to the event queue and distribute it to interested modules.
 
@@ -553,7 +605,23 @@ class BaseModule:
             v = event_kwargs.pop(o, None)
             if v is not None:
                 emit_kwargs[o] = v
-        event = self.make_event(*args, **event_kwargs)
+
+        # Two entry points:
+        #  - emit_event(data, ...)           -> create a new event via make_event()
+        #  - emit_event(existing_event, ...) -> update and re‑emit that event
+        if args and is_event(args[0]):
+            event, *rest = args
+            if rest:
+                self.warning(
+                    f"emit_event() was called on {self.name} with an existing event and extra "
+                    f"positional args ({rest}); extra args are ignored. "
+                    "Pass only the event plus keyword arguments, or call make_event() explicitly."
+                )
+            # Update the existing event (e.g. tags/context/module) before emitting
+            event = self.update_event(event, **event_kwargs)
+        else:
+            event = self.make_event(*args, **event_kwargs)
+
         if event is not None:
             children = event.children
             for e in [event] + children:
@@ -613,44 +681,32 @@ class BaseModule:
             asyncio.create_task(self._worker(), name=f"{self.scan.name}.{self.name}._worker()")
             for _ in range(self.module_threads)
         ]
-        self._event_handler_watchdog_task = asyncio.create_task(
+        watchdog_task = asyncio.create_task(
             self._event_handler_watchdog(),
             name=f"{self.scan.name}.{self.name}._event_handler_watchdog()",
         )
+        self._tasks.append(watchdog_task)
 
-    async def _setup(self):
-        """
-        Asynchronously sets up the module by invoking its 'setup()' method.
-
-        This method catches exceptions during setup, sets the module's error state if necessary, and determines the
-        status code based on the result of the setup process.
-
-        Args:
-            None
-
-        Returns:
-            tuple: A tuple containing the module's name, status (True for success, False for hard-fail, None for soft-fail),
-            and an optional status message.
-
-        Raises:
-            Exception: Captured exceptions from the 'setup()' method are logged, but not propagated.
-
-        Notes:
-            - The 'setup()' method can return either a simple boolean status or a tuple of status and message.
-            - A WordlistError exception triggers a soft-fail status.
-            - The debug log will contain setup status information for the module.
-        """
+    async def _setup(self, deps_only=False):
+        """ """
         status_codes = {False: "hard-fail", None: "soft-fail", True: "success"}
 
         status = False
         self.debug(f"Setting up module {self.name}")
         try:
-            result = await self.setup()
-            if type(result) == tuple and len(result) == 2:
-                status, msg = result
-            else:
-                status = result
-                msg = status_codes[status]
+            funcs = [self.setup_deps]
+            if not deps_only:
+                funcs.append(self.setup)
+            for func in funcs:
+                self.debug(f"Running {self.name}.{func.__name__}()")
+                result = await func()
+                if type(result) == tuple and len(result) == 2:
+                    status, msg = result
+                else:
+                    status = result
+                    msg = status_codes[status]
+                if status is False:
+                    break
             self.debug(f"Finished setting up module {self.name}")
         except Exception as e:
             self.set_error_state(f"Unexpected error during module setup: {e}", critical=True)
@@ -738,6 +794,9 @@ class BaseModule:
 
     @property
     def max_scope_distance(self):
+        """
+        Maximum scope distance for events that are accepted by the module.
+        """
         if self.in_scope_only or self.target_only:
             return 0
         if self.scope_distance_modifier is None:
@@ -785,10 +844,14 @@ class BaseModule:
             if "target" not in event.tags:
                 return False, "it did not meet target_only filter criteria"
 
-        # exclude certain URLs (e.g. javascript):
-        # TODO: revisit this after httpx rework
-        if event.type.startswith("URL") and self.name != "httpx" and "httpx-only" in event.tags:
-            return False, "its extension was listed in url_extension_httpx_only"
+        # limit js URLs to modules that opt in to receive them
+        if (not self.accept_url_special) and event.type.startswith("URL"):
+            extension = getattr(event, "url_extension", "")
+            if extension in self.scan.url_extension_special:
+                return (
+                    False,
+                    f"it is a special URL (extension {extension}) but the module does not opt in to receive special URLs",
+                )
 
         return True, "precheck succeeded"
 
@@ -1248,6 +1311,24 @@ class BaseModule:
 
         return r
 
+    async def api_download(self, url, **kwargs):
+        """
+        A wrapper around the `download()` web helper that incorporates API key cycling.
+        """
+        error = None
+        raise_error = kwargs.pop("raise_error", False)
+        for _ in range(self.api_retries):
+            new_url, kwargs = self.prepare_api_request(url, kwargs)
+            if "raise_error" not in kwargs:
+                kwargs["raise_error"] = True
+            try:
+                return await self.helpers.download(new_url, **kwargs)
+            except WebError as e:
+                error = e
+                self.cycle_api_key()
+        if raise_error:
+            raise error
+
     def _get_retry_after(self, r):
         # try to get retry_after from headers first
         headers = getattr(r, "headers", {})
@@ -1259,7 +1340,10 @@ class BaseModule:
                 if isinstance(body_json, dict):
                     retry_after = body_json.get("retry_after", None)
         if retry_after is not None:
-            return float(retry_after)
+            # we don't allow retry-after smaller than 1 second
+            # this is to prevent cases where APIs erroneously return a retry-after value of 0
+            # e.g. https://github.com/blacklanternsecurity/bbot/issues/2826
+            return max(1.0, float(retry_after))
 
     def _prepare_api_iter_req(self, url, page, page_size, offset, **requests_kwargs):
         """
@@ -1715,6 +1799,7 @@ class BaseInterceptModule(BaseModule):
     """
 
     accept_dupes = True
+    accept_url_special = True
     _intercept = True
 
     async def _worker(self):

bbot/modules/bucket_amazon.py

@@ -16,7 +16,7 @@ class bucket_amazon(bucket_template):
     }
     scope_distance_modifier = 3
 
-    cloud_helper_name = "amazon"
+    cloudcheck_provider_name = "Amazon"
     delimiters = ("", ".", "-")
     base_domains = ["s3.amazonaws.com"]
     regions = [None]

bbot/modules/bucket_digitalocean.py

@@ -15,7 +15,7 @@ class bucket_digitalocean(bucket_template):
         "permutations": "Whether to try permutations",
     }
 
-    cloud_helper_name = "digitalocean"
+    cloudcheck_provider_name = "DigitalOcean"
     delimiters = ("", "-")
     base_domains = ["digitaloceanspaces.com"]
     regions = ["ams3", "fra1", "nyc3", "sfo2", "sfo3", "sgp1"]

bbot/modules/bucket_firebase.py

@@ -15,7 +15,7 @@ class bucket_firebase(bucket_template):
         "permutations": "Whether to try permutations",
     }
 
-    cloud_helper_name = "google"
+    cloudcheck_provider_name = "Google"
     delimiters = ("", "-")
     base_domains = ["firebaseio.com"]
 

bbot/modules/bucket_google.py

@@ -19,7 +19,7 @@ class bucket_google(bucket_template):
         "permutations": "Whether to try permutations",
     }
 
-    cloud_helper_name = "google"
+    cloudcheck_provider_name = "Google"
     delimiters = ("", "-", ".", "_")
     base_domains = ["storage.googleapis.com"]
     bad_permissions = [

bbot/modules/{bucket_azure.py → bucket_microsoft.py}

@@ -1,7 +1,7 @@
 from bbot.modules.templates.bucket import bucket_template
 
 
-class bucket_azure(bucket_template):
+class bucket_microsoft(bucket_template):
     watched_events = ["DNS_NAME", "STORAGE_BUCKET"]
     produced_events = ["STORAGE_BUCKET", "FINDING"]
     flags = ["active", "safe", "cloud-enum", "web-basic"]
@@ -15,7 +15,7 @@ class bucket_azure(bucket_template):
         "permutations": "Whether to try permutations",
     }
 
-    cloud_helper_name = "azure"
+    cloudcheck_provider_name = "Microsoft"
     delimiters = ("", "-")
     base_domains = ["blob.core.windows.net"]
     # Dirbusting is required to know whether a bucket is public

bbot/modules/builtwith.py

@@ -33,7 +33,8 @@ class builtwith(subdomain_enum_apikey):
         subdomains = await self.query(query, parse_fn=self.parse_domains, request_fn=self.request_domains)
         if subdomains:
             for s in subdomains:
-                if s != event:
+                # `s` is a hostname string; compare against the event's data, not the Event object itself.
+                if s != event.data:
                     await self.emit_event(
                         s,
                         "DNS_NAME",
@@ -45,7 +46,8 @@ class builtwith(subdomain_enum_apikey):
             redirects = await self.query(query, parse_fn=self.parse_redirects, request_fn=self.request_redirects)
             if redirects:
                 for r in redirects:
-                    if r != event:
+                    # `r` is a hostname string; compare against the event's data, not the Event object itself.
+                    if r != event.data:
                         await self.emit_event(
                             r,
                             "DNS_NAME",

bbot/modules/dnsbimi.py

@@ -39,7 +39,7 @@ import re
 # Handle "v=BIMI1; l=https://bimi.entrust.net/example.com/logo.svg;"
 # Handle "v=BIMI1;l=https://bimi.entrust.net/example.com/logo.svg;a=https://bimi.entrust.net/example.com/certchain.pem"
 # Handle "v=BIMI1; l=https://bimi.entrust.net/example.com/logo.svg;a=https://bimi.entrust.net/example.com/certchain.pem;"
-_bimi_regex = r"^v=(?P<v>BIMI1);* *(l=(?P<l>https*://[^;]*|)|);*( *a=((?P<a>https://[^;]*|)|);*)*$"
+_bimi_regex = r"^v=(?P<v>BIMI1);\s?(?:l=(?P<l>https?://[^;\s]{1,255})?)?;?(?:\s?a=(?P<a>https://[^;\s]{1,255})?;?)?$"
 bimi_regex = re.compile(_bimi_regex, re.I)
 
 
@@ -140,6 +140,3 @@ class dnsbimi(BaseModule):
 
     async def handle_event(self, event):
         await self.inspectBIMI(event, event.host)
-
-
-# EOF