AirlockTools/utils/allowlist.py

#    Copyright (C) 2025 James Brotosky, Brandon Wickline
#
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU Affero General Public License as published
#    by the Free Software Foundation, either version 3 of the License, or
#    (at your option) any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU Affero General Public License for more details.
#
#    You should have received a copy of the GNU Affero General Public License
#    along with this program.  If not, see <https://www.gnu.org/licenses/>.
import datetime
import requests
import json
import os
import utils.pretty as ct
import ijson
import os
from bson import ObjectId
import datetime
import tqdm
import time

def pullPolicyExechistories(url, policiesnames, days, outputjson: bool):
    file_path = 'chunkinator.json'
    if not os.path.exists(file_path):
        with open(file_path, 'w') as file:
            json.dump({'error': 'Success', 'response': {'exechistories': []}}, file)
        print(f"File '{file_path}' has been crated.")
    else:
        print(f"File '{file_path}' already exists.")
    headers = {"X-APIKey": os.getenv('APIKEY')}
    checkpoint = str(skipback(days))
    json_output = {'error': 'Success', 'response': {'exechistories': []}}
    with tqdm.tqdm(total=100, desc="Total Percentage Complete: ") as pbar:
        while True:
            json_response_data = checkpoint_stomper(checkpoint, url, policiesnames, headers)
            histories = json_response_data['response']['exechistories']
            if not histories:
                break
            array_dividend =  max(round(len(histories) / 20), 1)
            match_found = False
            for index, item in enumerate(histories[::array_dividend]):
                if (datetime.date.today() - datetime.timedelta(days=days) <= datetime.datetime.strptime(item['datetime'].replace(' +0000 UTC', ''), '%Y-%m-%dT%H:%M:%SZ').date()):
                    match_found = True
                    break
            if match_found == True:
                for index, item in enumerate(tqdm.tqdm(histories, desc=f"Processing events for {checkpoint}", unit="events", colour="blue", initial=1)):
                    if index == len(histories) - 1:
                        checkpoint = item['checkpoint']
                        break
                    else:
                        if (datetime.date.today() - datetime.timedelta(days=days) > datetime.datetime.strptime(item['datetime'].replace(' +0000 UTC', ''), '%Y-%m-%dT%H:%M:%SZ').date()):
                            pass
                        else: json_output['response']['exechistories'].append(item)
            seen = {}
            if os.path.exists(file_path):
                with open(file_path, 'r') as file:
                    existing_data = json.load(file)
                    combined = existing_data['response']['exechistories']  + json_output['response']['exechistories']
            else:
                combined = json_output['response']['exechistories']
            for item in combined:
                key = (item.get('sha256'), item.get('filename'), item.get('hostname'))
                seen[key] = item
            deduplicated = list(seen.values())
            with open(file_path, 'w') as file:
                json.dump({'error': 'Success', 'response': {'exechistories': deduplicated}}, file)
            json_output['response']['exechistories'].clear()
            date_diff = datetime.date.today() - datetime.datetime.strptime(item['datetime'].replace(' +0000 UTC', ''), '%Y-%m-%dT%H:%M:%SZ').date()
            percentage_diff = ((days - date_diff.days) / 60) * 100
            pbar.n = round(percentage_diff)
            pbar.set_description_str(f"Total Percentage Complete: ({percentage_diff:.1f}%)")
            pbar.refresh
    with open(file_path, 'r') as file:
        final_output = json.load(file)
    os.remove(file_path)
    return json.dumps(final_output) if outputjson else None

def checkpoint_stomper(checkpoint, url, policy, headers):
    json_output = {'error': 'Success', 'response': {'exechistories': []}}
    endpoint = url + '/v1/logging/exechistories'
    payload_dict = {
        "type":[1,2,6,7],
        "checkpoint": checkpoint,
        "policy": [policy]
    }
    payload = json.dumps(payload_dict)
    with requests.request("POST", endpoint, headers=headers, data=payload, verify=False, stream=True) as response:
        parser = ijson.items(response.raw, 'response.exechistories.item')
        for item in parser:
            key = (item.get('sha256'), item.get('hostname'))
            if key not in json_output:
                json_output['response']['exechistories'].append(item)   
    parse_text = json.loads(json.dumps(json_output))
    return parse_text

def listPolicies(url): 
    endpoint = url + '/v1/group'
    print(ct.colorText("[+] Grabbing All Policies", "cyan"))
    payload = {}
    headers = {
        "X-APIKey": os.getenv('APIKEY')
    }
    response = requests.request("POST", endpoint, headers=headers, data=payload, verify=False)
    parse_text = json.loads(response.text)
    policiesnames = []
    policyids = []
    for index, list in enumerate(parse_text['response']['groups'], start=1):
        print(ct.colorText(f"{index}. {list['name']}", "yellow"))
        policiesnames.append(list['name'])
        policyids.append(list['groupid'])
    choice = input(ct.colorText("Select Policy Group: ", "white"))
    choice = int(choice) - 1
    return choice, policiesnames, policyids

def listAllowlists(url): 
    endpoint = url + '/v1/application'
    print(ct.colorText("[+] Grabbing All Allowlists", "cyan"))
    payload = {}
    headers = {
        "X-APIKey": os.getenv('APIKEY')
    }
    response = requests.request("POST", endpoint, headers=headers, data=payload, verify=False)
    parse_text = json.loads(response.text)
    policiesnames = []
    policyids = []
    for index, list in enumerate(parse_text['response']['applications'], start=1):
        if index >= 38:
            print(ct.colorText(f"{index}. {list['name']}", "yellow"))
            policiesnames.append(list['name'])
            policyids.append(list['applicationid'])
    choice = int(input(ct.colorText("Select allowlist: ", "white")))
    if choice < 38:
        print(ct.colorText("Please only choose an allowlist designed for this use - '38+'","red"))
    elif choice >= 38:
        choice = choice - 38
        return choice, policiesnames, policyids
    #Need else and catch for upper bound

def skipback(days):
    """
    Generate a MongoDB ObjectId for a given number of days ago from today.
    Adds 1 extra day to the input to look further back.
    """
    adjusted_days = days + 1
    date_days_ago = datetime.datetime.now(datetime.UTC) - datetime.timedelta(days=adjusted_days)
    timestamp = int(date_days_ago.timestamp())
    hex_timestamp = format(timestamp, '08x')
    objectid_hex = hex_timestamp + '0000000000000000'
    return ObjectId(objectid_hex)