diff --git a/AirlockTools.py b/AirlockTools.py index 2d86f1b..2008288 100644 --- a/AirlockTools.py +++ b/AirlockTools.py @@ -14,11 +14,8 @@ # along with this program. If not, see . import dotenv -import gc -import json import os import pandas as pd -import re import urllib3 import utils.allowlist import utils.getdeviceevents @@ -41,7 +38,6 @@ path_exclusion_constant = 3 min_files_for_path = 4 threat_tolerance_constant = 4 - def apivalidation(): match os.getenv('APIKEY'): case '': @@ -140,9 +136,12 @@ def menu_prepare_to_enforce(): first_policy = " " second_policy = " " - allowlist_parent_name = " " - allowlist_child_name = " " destination_name = " " + destination_id = " " + allowlist_parent_name = " " + allowlist_parent_id = " " + allowlist_child_name = " " + allowlist_child_id = " " #If the directorys where we're going to store our output dont exist, make them. if not os.path.exists("parquet"): os.makedirs("parquet") @@ -176,247 +175,34 @@ def menu_prepare_to_enforce(): elif choice == "2": if not os.path.exists(f"parquet\\execution_history_{first_policy}.parquet"): - print(choice) - print(first_policy) - - exe1 = utils.allowlist.pullPolicyExechistories(url, first_policy, 60, True) - data = json.loads(exe1) - executionhist_policy1 = pd.DataFrame(data["response"]["exechistories"]) - - if not executionhist_policy1.empty: - executionhist_policy1 = executionhist_policy1[['sha256', 'publisher', 'filename', 'hostname', 'username', 'pprocess', 'gprocess', 'commandline']] - executionhist_policy1 = executionhist_policy1.drop_duplicates(subset=['sha256', 'filename', 'hostname']) - executionhist_policy1 = executionhist_policy1.sort_values(by=['sha256', 'filename']) - - executionhist_policy1.to_parquet(f"parquet\\execution_history_{first_policy}.parquet", index=False) - print(ct.colorText(f"Staging of Execution history for policy: {first_policy} is complete", "green")) - - del data - del exe1 - del executionhist_policy1 - - gc.collect() + utils.policyfunctions.getPolicyInfo(url, first_policy, 60) if not os.path.exists(f"parquet\\execution_history_{second_policy}.parquet"): - exe2 = utils.allowlist.pullPolicyExechistories(url,second_policy, 60, True) - data2 = json.loads(exe2) - executionhist_policy2 = pd.DataFrame(data2["response"]["exechistories"]) - - if not executionhist_policy2.empty: - executionhist_policy2 = executionhist_policy2[['sha256', 'publisher', 'filename', 'hostname', 'username', 'pprocess', 'gprocess', 'commandline']] - executionhist_policy2 = executionhist_policy2.drop_duplicates(subset=['sha256', 'filename', 'hostname']) - executionhist_policy2 = executionhist_policy2.sort_values(by=['sha256', 'filename']) - - executionhist_policy2.to_parquet(f"parquet\\execution_history_{second_policy}.parquet", index=False) - print(ct.colorText(f"Staging of Execution history for policy: {second_policy} is complete", "green")) - - del executionhist_policy2 - del data2 - del exe2 - - gc.collect() + utils.policyfunctions.getPolicyInfo(url, second_policy, 60) if not os.path.exists(f"parquet\\combined_hashlist_{first_policy}_{second_policy}.parquet"): - combined_hashes = pd.DataFrame(columns=['sha256', 'publisher']) - hashes = [] - - try: - hash1 = pd.read_parquet(f"parquet\\execution_history_{first_policy}.parquet", columns=['sha256', 'publisher']) - utils.pathfunctions.inspect_parquet(f"parquet\\execution_history_{first_policy}.parquet") - if not hash1.empty: - hashes.append(hash1) - else: - print("⚠️ First dataframe is empty.") - except Exception as e: - print(f"❌ Error reading first Parquet file: {e}") - - try: - hash2 = pd.read_parquet(f"parquet\\execution_history_{second_policy}.parquet", columns=['sha256', 'publisher']) - utils.pathfunctions.inspect_parquet(f"parquet\\execution_history_{second_policy}.parquet") - if not hash2.empty: - hashes.append(hash2) - else: - print("⚠️ Second dataframe is empty.") - except Exception as e: - print(f"❌ Error reading second Parquet file: {e}") - - if hashes: - combined_hashes = pd.concat(hashes, ignore_index=True) - print(f"✅ Combined {len(combined_hashes)} hashes.") - else: - print("⚠️ No valid dataframes to combine.") - - combined_hashes = combined_hashes.drop_duplicates(subset=['sha256']) - augmented_combo = utils.hashfunctions.augmentAggregatedHashes(url, combined_hashes) - - numeric_reputation_cols = [ - 'reputation_scannermatch', - 'reputation_scannercount', - 'reputation_threatlevel' - ] - - for col in numeric_reputation_cols: - if col in augmented_combo.columns: - augmented_combo[col] = pd.to_numeric(augmented_combo[col].replace('N/A', pd.NA), errors='coerce') - - augmented_combo = augmented_combo.rename(columns={'publisher_x': 'publisher'}) - augmented_combo = augmented_combo[['sha256', 'publisher', 'description', 'productname', 'productversion', - 'reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount', - 'reputation_status', 'reputation_threatlevel', 'reputation_threatname', - 'reputation_timestamp']] - augmented_combo = augmented_combo.sort_values(by=['publisher', 'description', 'productname']) - augmented_combo.to_parquet(f"parquet\\combined_hashlist_{first_policy}_{second_policy}.parquet", index=False) - - del combined_hashes - del augmented_combo - gc.collect() - - print(ct.colorText("Hash reputation info added to dataframe", "green")) + utils.hashfunctions.combineHashes(url, first_policy, second_policy) if not os.path.exists(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet") and not os.path.exists(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet") and not os.path.exists(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet"): - - # Categorize the hashes - categorized = utils.hashfunctions.categorizeHashes( + utils.hashfunctions.categorizeHashes( + first_policy, + second_policy, pd.read_parquet(f"parquet\\combined_hashlist_{first_policy}_{second_policy}.parquet"), threat_tolerance_constant, bad_publisher_list, pups ) - - categorized[0].to_parquet(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet", index=False) - categorized[1].to_parquet(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet", index=False) - categorized[2].to_parquet(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet", index=False) - - del categorized - gc.collect() - + if not os.path.exists(f"parquet\\condensed_executions_{first_policy}_{second_policy}.parquet"): - # Condense execution history - try: - exe1 = pd.read_parquet(f"parquet\\execution_history_{first_policy}.parquet") - utils.pathfunctions.inspect_parquet(f"parquet\\execution_history_{first_policy}.parquet") - if not exe1.empty: - print() - else: - print("⚠️ First dataframe is empty.") - except Exception as e: - print(f"❌ Error reading first Parquet file: {e}") - - try: - exe2 = pd.read_parquet(f"parquet\\execution_history_{second_policy}.parquet") - utils.pathfunctions.inspect_parquet(f"parquet\\execution_history_{second_policy}.parquet") - if not exe2.empty: - print() - else: - print("⚠️ Second dataframe is empty.") - except Exception as e: - print(f"❌ Error reading second Parquet file: {e}") - - if not exe1.empty and not exe2.empty: - condensed_combo = pd.concat([exe1, exe2], ignore_index=True) - - print(f"✅ Combined {len(condensed_combo)} hashes.") - elif exe1.empty: - condensed_combo = exe2 - elif exe2.empty: - condensed_combo = exe1 - else: - print("⚠️ No valid dataframes to combine.") - - condensed_combo.to_parquet(f"parquet\\condensed_executions_{first_policy}_{second_policy}.parquet", index=False) - del condensed_combo - gc.collect() - - - + utils.hashfunctions.condenseExecutions(first_policy,second_policy) if os.path.exists(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet") & os.path.exists(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet") & os.path.exists(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet"): + utils.hashfunctions.divideSortedHashExecutions(first_policy,second_policy,pups) - utils.hashfunctions.combineHashAndHist(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet", first_policy, second_policy) - utils.hashfunctions.combineHashAndHist(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet", first_policy, second_policy) - utils.hashfunctions.combineHashAndHist(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet", first_policy, second_policy) - - unknown = pd.read_parquet(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet") - good = pd.read_parquet(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet") - bad = pd.read_parquet(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet") - - # Build regex pattern once - pattern = utils.pathfunctions.regulator(pups) - - # Move matching rows from unknown and good to bad - bad = pd.concat([ - bad, - unknown[unknown["filename"].str.contains(pattern, na=False)], - good[good["filename"].str.contains(pattern, na=False)] - ], ignore_index=True) - - # Remove matching rows from unknown and good - unknown = unknown[~unknown["filename"].str.contains(pattern, na=False)] - good = good[~good["filename"].str.contains(pattern, na=False)] - - unknown.to_csv(f"needs_approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv",index=False) - good.to_csv(f"needs_approved\\hashes_rep_good_{first_policy}_{second_policy}.csv",index=False) - bad.to_csv(f"needs_approved\\hashes_rep_bad_{first_policy}_{second_policy}.csv",index=False) - - ct.style_dataframe_dark(unknown, f"needs_approved\\hashes_rep_unknown_{first_policy}_{second_policy}.html") - ct.style_dataframe_dark(good, f"needs_approved\\hashes_rep_good_{first_policy}_{second_policy}.html") - ct.style_dataframe_dark(bad, f"needs_approved\\hashes_rep_bad_{first_policy}_{second_policy}.html") - elif choice == "3": if os.path.exists(f"approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv") and os.path.exists(f"approved\\hashes_rep_good_{first_policy}_{second_policy}.csv"): - - if not os.path.exists(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet"): - - df1 = tryToReadCSV(f"approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv") - df2 = tryToReadCSV(f"approved\\hashes_rep_good_{first_policy}_{second_policy}.csv") - - all_approved_hashes = pd.concat([df1 , df2], ignore_index=True).sort_values(by=['filename']) - - - - print(ct.colorText(f"Approved hash lists have been combined","green")) - - all_approved_hashes.to_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet", index=False) - del all_approved_hashes - gc.collect() - - if not os.path.exists(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet"): - all_approved_hashes = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet") - print(ct.colorText(f"Beginning calculating longest common filepaths for path exceptions","green")) - - haslcp = utils.pathfunctions.split_filepaths_grouped(all_approved_hashes) - haslcp.drop_duplicates() - - forbidden = utils.pathfunctions.regulator(badpathparts, True) - forbidden_lcfp = haslcp["longestcfp"].str.contains(forbidden, na=False) - - - print(ct.colorText("Removing forbidden filepaths for path exceptions", "green")) - - # Make a real DataFrame copy before modifying - lcp_not_forbidden = haslcp[~forbidden_lcfp].copy() - - - #For the review, drop down to only the columns we care, and then group by the commmon file path, consolidating and dropping dupes - lcp_not_forbidden_review = lcp_not_forbidden[['longestcfp', 'middle', 'filename_only', 'sha256']] - - # Count unique sha256 per longestcfp - unique_sha_counts = lcp_not_forbidden_review.groupby('longestcfp')['sha256'].nunique().reset_index() - unique_sha_counts.columns = ['longestcfp', 'unique_sha256_count'] - - # Merge the count back into the original DataFrame - lcp_not_forbidden_review = lcp_not_forbidden_review.merge(unique_sha_counts, on='longestcfp', how='left') - lcp_not_forbidden_review = lcp_not_forbidden_review[lcp_not_forbidden_review['unique_sha256_count'] >= min_files_for_path] - - - - - - lcp_not_forbidden_review.to_parquet(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet",index=False) - lcp_not_forbidden_review.to_csv(f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.csv",index=False) - - + utils.pathfunctions.generatePathReview(first_policy, second_policy, badpathparts, min_files_for_path) else: print(ct.colorText(f"Please manually approve hashes prior to this step","red")) @@ -424,26 +210,7 @@ def menu_prepare_to_enforce(): if os.path.exists(f"approved\\path_needs_approved_{first_policy}_{second_policy}.csv"): if not os.path.exists(f"parquet\\final_hash_approvals_{first_policy}_{second_policy}.parquet") and not os.path.exists(f"parquet\\final_path_exclusions_{first_policy}_{second_policy}.parquet"): - allhashes = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet") - - pathexclusions = tryToReadCSV(f"approved\\path_needs_approved_{first_policy}_{second_policy}.csv") - pathexclusions.to_parquet(f"parquet\\final_path_exclusions_{first_policy}_{second_policy}.parquet", index=False) - - allowbyhash = allhashes[~allhashes['sha256'].isin(pathexclusions['sha256'])] - - allowbyhash.to_parquet(f"parquet\\final_hash_approvals_{first_policy}_{second_policy}.parquet", index=False) - - allowbyhash.sort_values(by=["filename"]) - - ct.style_dataframe_dark(allowbyhash, f"preflight\\final_hash_approvals_{first_policy}_{second_policy}.html") - ct.style_dataframe_dark(pathexclusions, f"preflight\\final_path_exclusions_{first_policy}_{second_policy}.html") - - - del allowbyhash - del pathexclusions - gc.collect() - - + utils.hashfunctions.generatePreflights(first_policy, second_policy) elif choice == "5": @@ -467,47 +234,16 @@ def menu_prepare_to_enforce(): elif choice == "6": if os.path.exists(f"preflight\\final_path_exclusions_{first_policy}_{second_policy}.html") and os.path.exists(f"preflight\\final_hash_approvals_{first_policy}_{second_policy}.html") and allowlist_parent_name != " " and allowlist_child_name != " " and destination_name != " ": - - pathexclusions = pd.read_parquet(f"parquet\\final_path_exclusions_{first_policy}_{second_policy}.parquet") - allowbyhash = pd.read_parquet(f"parquet\\final_hash_approvals_{first_policy}_{second_policy}.parquet") - - ct.areYouSure() - confirmation = input(ct.colorText("Type 'I AGREE' to continue: ","white")) - - if confirmation.strip().upper() == "I AGREE": - print(ct.colorText("Proceeding with the code...", "yellow")) - print(ct.colorText(f"Adding path exclusions to {destination_name}", "yellow")) - pathexcludelist = pathexclusions['longestcfp'].unique().tolist() - - - - # Regex to match a Windows drive letter at the start (e.g., C:\) - drive_letter_pattern = re.compile(r'^[a-zA-Z]:\\') - - # Processed list - processed_paths = [ - (path if drive_letter_pattern.match(path) else f"\\\\{path}") + "**" - for path in pathexcludelist -] - - utils.policyfunctions.addPath(destination_id,processed_paths) - - print(ct.colorText(f"Adding hashes to {allowlist_parent_name}", "yellow")) - - allowlist_parenthashlist = allowbyhash[allowbyhash['reputation_status'] == 'KNOWN']['sha256'].unique().tolist() - utils.policyfunctions.addHash(allowlist_parent_id,allowlist_parenthashlist) - - print(ct.colorText(f"Adding hashes to {allowlist_child_name}", "yellow")) - allowlist_childhashlist = allowbyhash[allowbyhash['reputation_status'] == 'UNKNOWN']['sha256'].unique().tolist() - utils.policyfunctions.addHash(allowlist_child_id, allowlist_childhashlist) - - ct.locked() - - exit() - - else: - print(ct.colorText("Operation aborted. You MUST EXPLICITLY AGREE to proceed.", "red")) - break + utils.policyfunctions.sendToPolicy( + first_policy, + second_policy, + destination_name, + destination_id, + allowlist_parent_name, + allowlist_parent_id, + allowlist_child_name, + allowlist_child_id + ) elif choice == "Q": break diff --git a/utils/hashfunctions.py b/utils/hashfunctions.py index a9e0e17..d617118 100644 --- a/utils/hashfunctions.py +++ b/utils/hashfunctions.py @@ -12,15 +12,15 @@ # # You should have received a copy of the GNU Affero General Public License # along with this program. If not, see . - +import gc +import json +import os import pandas as pd import requests -import os -import json import utils.pathfunctions as pathf +import utils.hashfunctions as hashf import utils.pretty as ct -import gc - +from AirlockTools import tryToReadCSV def aggregateHashes(executions_json) -> pd.DataFrame: """ @@ -104,7 +104,7 @@ def augmentAggregatedHashes(url, agg_df: pd.DataFrame) -> pd.DataFrame: return aug_df -def categorizeHashes(df: pd.DataFrame, threat_tolerance: int, untrusted_publishers, pups: list): +def categorizeHashes(first_policy, second_policy, df: pd.DataFrame, threat_tolerance: int, untrusted_publishers, pups: list): if untrusted_publishers is None: untrusted_publishers = [] if pups is None: pups = [] @@ -144,9 +144,14 @@ def categorizeHashes(df: pd.DataFrame, threat_tolerance: int, untrusted_publishe approved_df = df[mask_approved] unapproved_df = df[~(mask_needsreview | mask_approved)] - return needsreview_df, approved_df, unapproved_df - + needsreview_df.to_parquet(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet", index=False) + approved_df.to_parquet(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet", index=False) + unapproved_df.to_parquet(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet", index=False) + del needsreview_df + del approved_df + del unapproved_df + gc.collect() def explode_and_deduplicate(df): df['sha256'] = df['sha256'].str.split(',') @@ -221,4 +226,150 @@ def combineHashAndHist(path, first_policy, second_policy): df.to_parquet(path, index=False) del df del condensed_combo + gc.collect() + +def combineHashes(url, first_policy, second_policy): + combined_hashes = pd.DataFrame(columns=['sha256', 'publisher']) + hashes = [] + try: + hash1 = pd.read_parquet(f"parquet\\execution_history_{first_policy}.parquet", columns=['sha256', 'publisher']) + pathf.inspect_parquet(f"parquet\\execution_history_{first_policy}.parquet") + if not hash1.empty: + hashes.append(hash1) + else: + print("⚠️ First dataframe is empty.") + except Exception as e: + print(f"❌ Error reading first Parquet file: {e}") + + try: + hash2 = pd.read_parquet(f"parquet\\execution_history_{second_policy}.parquet", columns=['sha256', 'publisher']) + pathf.inspect_parquet(f"parquet\\execution_history_{second_policy}.parquet") + if not hash2.empty: + hashes.append(hash2) + else: + print("⚠️ Second dataframe is empty.") + except Exception as e: + print(f"❌ Error reading second Parquet file: {e}") + + if hashes: + combined_hashes = pd.concat(hashes, ignore_index=True) + print(f"✅ Combined {len(combined_hashes)} hashes.") + else: + print("⚠️ No valid dataframes to combine.") + + combined_hashes = combined_hashes.drop_duplicates(subset=['sha256']) + augmented_combo = hashf.augmentAggregatedHashes(url, combined_hashes) + + numeric_reputation_cols = [ + 'reputation_scannermatch', + 'reputation_scannercount', + 'reputation_threatlevel' + ] + + for col in numeric_reputation_cols: + if col in augmented_combo.columns: + augmented_combo[col] = pd.to_numeric(augmented_combo[col].replace('N/A', pd.NA), errors='coerce') + + augmented_combo = augmented_combo.rename(columns={'publisher_x': 'publisher'}) + augmented_combo = augmented_combo[['sha256', 'publisher', 'description', 'productname', 'productversion', + 'reputation_lastseen', 'reputation_scannermatch', 'reputation_scannercount', + 'reputation_status', 'reputation_threatlevel', 'reputation_threatname', + 'reputation_timestamp']] + augmented_combo = augmented_combo.sort_values(by=['publisher', 'description', 'productname']) + augmented_combo.to_parquet(f"parquet\\combined_hashlist_{first_policy}_{second_policy}.parquet", index=False) + + del combined_hashes + del augmented_combo + gc.collect() + print(ct.colorText("Hash reputation info added to dataframe", "green")) + +def condenseExecutions(first_policy,second_policy): + exe1 = pd.DataFrame() + exe2 = pd.DataFrame() + condensed_combo = pd.DataFrame() + + try: + exe1 = pd.read_parquet(f"parquet\\execution_history_{first_policy}.parquet") + pathf.inspect_parquet(f"parquet\\execution_history_{first_policy}.parquet") + if not exe1.empty: + print() + else: + print("⚠️ First dataframe is empty.") + except Exception as e: + print(f"❌ Error reading first Parquet file: {e}") + + try: + exe2 = pd.read_parquet(f"parquet\\execution_history_{second_policy}.parquet") + pathf.inspect_parquet(f"parquet\\execution_history_{second_policy}.parquet") + if not exe2.empty: + print() + else: + print("⚠️ Second dataframe is empty.") + except Exception as e: + print(f"❌ Error reading second Parquet file: {e}") + + if not exe1.empty and not exe2.empty: + condensed_combo = pd.concat([exe1, exe2], ignore_index=True) + + print(f"✅ Combined {len(condensed_combo)} hashes.") + elif exe1.empty: + condensed_combo = exe2 + elif exe2.empty: + condensed_combo = exe1 + else: + print("⚠️ No valid dataframes to combine.") + + condensed_combo.to_parquet(f"parquet\\condensed_executions_{first_policy}_{second_policy}.parquet", index=False) + del condensed_combo + gc.collect() + +def divideSortedHashExecutions(first_policy,second_policy, pups): + + combineHashAndHist(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet", first_policy, second_policy) + combineHashAndHist(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet", first_policy, second_policy) + combineHashAndHist(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet", first_policy, second_policy) + + unknown = pd.read_parquet(f"parquet\\hashes_rep_unknown_{first_policy}_{second_policy}.parquet") + good = pd.read_parquet(f"parquet\\hashes_rep_good_{first_policy}_{second_policy}.parquet") + bad = pd.read_parquet(f"parquet\\hashes_rep_bad_{first_policy}_{second_policy}.parquet") + + # Build regex pattern once + pattern = pathf.regulator(pups) + + # Move matching rows from unknown and good to bad + bad = pd.concat([ + bad, + unknown[unknown["filename"].str.contains(pattern, na=False)], + good[good["filename"].str.contains(pattern, na=False)] + ], ignore_index=True) + + # Remove matching rows from unknown and good + unknown = unknown[~unknown["filename"].str.contains(pattern, na=False)] + good = good[~good["filename"].str.contains(pattern, na=False)] + + unknown.to_csv(f"needs_approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv",index=False) + good.to_csv(f"needs_approved\\hashes_rep_good_{first_policy}_{second_policy}.csv",index=False) + bad.to_csv(f"needs_approved\\hashes_rep_bad_{first_policy}_{second_policy}.csv",index=False) + + ct.style_dataframe_dark(unknown, f"needs_approved\\hashes_rep_unknown_{first_policy}_{second_policy}.html") + ct.style_dataframe_dark(good, f"needs_approved\\hashes_rep_good_{first_policy}_{second_policy}.html") + ct.style_dataframe_dark(bad, f"needs_approved\\hashes_rep_bad_{first_policy}_{second_policy}.html") + +def generatePreflights(first_policy, second_policy): + allhashes = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet") + + pathexclusions = tryToReadCSV(f"approved\\path_needs_approved_{first_policy}_{second_policy}.csv") + pathexclusions.to_parquet(f"parquet\\final_path_exclusions_{first_policy}_{second_policy}.parquet", index=False) + + allowbyhash = allhashes[~allhashes['sha256'].isin(pathexclusions['sha256'])] + + allowbyhash.to_parquet(f"parquet\\final_hash_approvals_{first_policy}_{second_policy}.parquet", index=False) + + allowbyhash.sort_values(by=["filename"]) + + ct.style_dataframe_dark(allowbyhash, f"preflight\\final_hash_approvals_{first_policy}_{second_policy}.html") + ct.style_dataframe_dark(pathexclusions, f"preflight\\final_path_exclusions_{first_policy}_{second_policy}.html") + + del allowbyhash + del pathexclusions gc.collect() \ No newline at end of file diff --git a/utils/pathfunctions.py b/utils/pathfunctions.py index 336a515..f615251 100644 --- a/utils/pathfunctions.py +++ b/utils/pathfunctions.py @@ -12,11 +12,14 @@ # # You should have received a copy of the GNU Affero General Public License # along with this program. If not, see . - -import pandas as pd -import os import ast +import gc +import os +import pandas as pd import re +import utils.pathfunctions as pathf +import utils.pretty as ct +from AirlockTools import tryToReadCSV def split_filepaths_grouped(df, col="filename", group_parts=3, min_parts=3): @@ -133,3 +136,49 @@ def regulator(paths, case_insensitive=True): print(f"Regulator is providing: {pattern}") return pattern +def generatePathReview(first_policy, second_policy, badpathparts, min_files_for_path): + + if not os.path.exists(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet"): + + df1 = tryToReadCSV(f"approved\\hashes_rep_unknown_{first_policy}_{second_policy}.csv") + df2 = tryToReadCSV(f"approved\\hashes_rep_good_{first_policy}_{second_policy}.csv") + + all_approved_hashes = pd.concat([df1 , df2], ignore_index=True).sort_values(by=['filename']) + + + + print(ct.colorText(f"Approved hash lists have been combined","green")) + + all_approved_hashes.to_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet", index=False) + del all_approved_hashes + gc.collect() + + if not os.path.exists(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet"): + all_approved_hashes = pd.read_parquet(f"parquet\\all_approved_hashes_{first_policy}_{second_policy}.parquet") + print(ct.colorText(f"Beginning calculating longest common filepaths for path exceptions","green")) + + haslcp = pathf.split_filepaths_grouped(all_approved_hashes) + haslcp.drop_duplicates() + + forbidden = pathf.regulator(badpathparts, True) + forbidden_lcfp = haslcp["longestcfp"].str.contains(forbidden, na=False) + + + print(ct.colorText("Removing forbidden filepaths for path exceptions", "green")) + + # Make a real DataFrame copy before modifying + lcp_not_forbidden = haslcp[~forbidden_lcfp].copy() + + #For the review, drop down to only the columns we care, and then group by the commmon file path, consolidating and dropping dupes + lcp_not_forbidden_review = lcp_not_forbidden[['longestcfp', 'middle', 'filename_only', 'sha256']] + + # Count unique sha256 per longestcfp + unique_sha_counts = lcp_not_forbidden_review.groupby('longestcfp')['sha256'].nunique().reset_index() + unique_sha_counts.columns = ['longestcfp', 'unique_sha256_count'] + + # Merge the count back into the original DataFrame + lcp_not_forbidden_review = lcp_not_forbidden_review.merge(unique_sha_counts, on='longestcfp', how='left') + lcp_not_forbidden_review = lcp_not_forbidden_review[lcp_not_forbidden_review['unique_sha256_count'] >= min_files_for_path] + + lcp_not_forbidden_review.to_parquet(f"parquet\\path_needs_approved_{first_policy}_{second_policy}.parquet",index=False) + lcp_not_forbidden_review.to_csv(f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.csv",index=False) \ No newline at end of file diff --git a/utils/policyfunctions.py b/utils/policyfunctions.py index 2dd5d18..5b26a65 100644 --- a/utils/policyfunctions.py +++ b/utils/policyfunctions.py @@ -12,11 +12,17 @@ # # You should have received a copy of the GNU Affero General Public License # along with this program. If not, see . - -import requests +import gc import json import os +import pandas as pd +import re +import requests import utils.pretty as ct +import utils.allowlist + + + def addHash(policy, hash): print(f"Adding the following hashes to {policy}:") @@ -65,3 +71,57 @@ def addPathReal(url, grouplistID, pathlist): except requests.exceptions.RequestException as e: return {"error": str(e)} +def getPolicyInfo(url, policy, days): + executionhist_policy = pd.DataFrame() + exehist = utils.allowlist.pullPolicyExechistories(url, policy, days, True) + data = json.loads(exehist) + executionhist_policy = pd.DataFrame(data["response"]["exechistories"]) + if not executionhist_policy.empty: + executionhist_policyxecutionhist_policy = executionhist_policy[['sha256', 'publisher', 'filename', 'hostname', 'username', 'pprocess', 'gprocess', 'commandline']] + executionhist_policy = executionhist_policy.drop_duplicates(subset=['sha256', 'filename', 'hostname']) + executionhist_policy = executionhist_policy.sort_values(by=['sha256', 'filename']) + executionhist_policy.to_parquet(f"parquet\\execution_history_{policy}.parquet", index=False) + print(ct.colorText(f"Staging of Execution history for policy: {policy} is complete", "green")) + del data + del exehist + gc.collect() + return executionhist_policy + +def sendToPolicy(first_policy, second_policy, destination_name, destination_id, allowlist_parent_name, allowlist_parent_id, allowlist_child_name, allowlist_child_id): + pathexclusions = pd.read_parquet(f"parquet\\final_path_exclusions_{first_policy}_{second_policy}.parquet") + allowbyhash = pd.read_parquet(f"parquet\\final_hash_approvals_{first_policy}_{second_policy}.parquet") + + ct.areYouSure() + confirmation = input(ct.colorText("Type 'I AGREE' to continue: ","white")) + + if confirmation.strip().upper() == "I AGREE": + print(ct.colorText("Proceeding with the code...", "yellow")) + print(ct.colorText(f"Adding path exclusions to {destination_name}", "yellow")) + pathexcludelist = pathexclusions['longestcfp'].unique().tolist() + + # Regex to match a Windows drive letter at the start (e.g., C:\) + drive_letter_pattern = re.compile(r'^[a-zA-Z]:\\') + + # Processed list + processed_paths = [ + (path if drive_letter_pattern.match(path) else f"\\\\{path}") + "**" + for path in pathexcludelist +] + addPath(destination_id,processed_paths) + + print(ct.colorText(f"Adding hashes to {allowlist_parent_name}", "yellow")) + + allowlist_parenthashlist = allowbyhash[allowbyhash['reputation_status'] == 'KNOWN']['sha256'].unique().tolist() + addHash(allowlist_parent_id,allowlist_parenthashlist) + + print(ct.colorText(f"Adding hashes to {allowlist_child_name}", "yellow")) + allowlist_childhashlist = allowbyhash[allowbyhash['reputation_status'] == 'UNKNOWN']['sha256'].unique().tolist() + addHash(allowlist_child_id, allowlist_childhashlist) + + ct.locked() + + exit() + + else: + print(ct.colorText("Operation aborted. You MUST EXPLICITLY AGREE to proceed.", "red")) + \ No newline at end of file diff --git a/utils/pretty.py b/utils/pretty.py index 851dfce..3463d74 100644 --- a/utils/pretty.py +++ b/utils/pretty.py @@ -1,6 +1,5 @@ import os - def colorText(text: str, color: str) -> str: colors = { "red": "\033[91m", @@ -240,11 +239,6 @@ def printEnforceChecklist(first_policy, second_policy, allowlist_child_name, all else: print(colorText(" [✗] The combined approved hashes list has not been generated","red")) - if os.path.exists(f"parquet\\approved_hashes_with_paths_{first_policy}_{second_policy}.parquet"): - print(colorText(" [✓] Longest common filepaths have been generated and appended to hash info","green")) - else: - print(colorText(" [✗] Longest common filepaths have not been generated","red")) - if os.path.exists(f"needs_approved\\path_needs_approved_{first_policy}_{second_policy}.csv"): print(colorText(" [✓] Path review list created","green")) else: