├── .gitignore ├── apiCreds.py ├── .gitattributes ├── assets └── screenshot.png ├── README.md ├── malget.py └── LICENSE /.gitignore: -------------------------------------------------------------------------------- 1 | 2 | 3 | -------------------------------------------------------------------------------- /apiCreds.py: -------------------------------------------------------------------------------- 1 | VTKEY = "PLACE API KEY HERE" 2 | MALSHAREKEY = "PLACE API KEY HERE" -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- 1 | # Auto detect text files and perform LF normalization 2 | * text=auto 3 | -------------------------------------------------------------------------------- /assets/screenshot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Droogy/Malget/HEAD/assets/screenshot.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Malget 2 | 3 | Your own personal malware feed! 4 | 5 | ## Description 6 | 7 | Malget is a Python script which downloads, classifies, and names the latest malware samples from Malshare with a little help from the VirusTotal API. 8 | 9 | I created this originally because I was practicing creating YARA, Sigma, and Snort rules but I didn't have live samples to work with. While you can get samples from some databases they may not be updated often or it becomes tedious grabbing a sample, dragging it over to a folder, naming it, etc.. 10 | 11 | ## Example Output 12 | 13 | ![Screenshot](assets/screenshot.png) 14 | 15 | ## Getting Started 16 | ### Dependencies 17 | 18 | * You must have VirusTotal and Malshare API keys for this program to work 19 | * [How to get VirusTotal API Key](https://support.virustotal.com/hc/en-us/articles/115002088769-Please-give-me-an-API-key) 20 | * [How to get Malshare API Key](https://malshare.com/register.php) 21 | * Once you have the keys, place them in [apiCreds.py](apiCreds.py) and you are good to go 22 | * all of the libraries used in Malget are in the Python Standard Library 23 | 24 | ### Executing program 25 | 26 | * the `-n` argument is used the specify the number of samples you want to download (note that Malshare and VirusTotal have daily API limits) 27 | ```python 28 | # download and classify 10 samples 29 | python3 malget.py -n 10 30 | ``` 31 | ## To-Do 32 | * multi-thread everything 33 | * need more error handling 34 | * unit testing and profiling sessions are needed to help refactor code 35 | * add more magic bytes signatures and respective folders 36 | ## Help 37 | 38 | ``` 39 | python3 malget.py --help 40 | ``` 41 | 42 | ## Authors 43 | 44 | [@0xDroogy](https://twitter.com/0xDroogy) 45 | 46 | A special thanks to [smelly](https://twitter.com/smelly__vx) and the [VX-Underground](https://twitter.com/vxunderground) crew for inspiration from their own malware feed :) -------------------------------------------------------------------------------- /malget.py: -------------------------------------------------------------------------------- 1 | # Malget by Droogy 2 | # 3 | # Your own personal malware feed! 4 | # 5 | 6 | from apiCreds import MALSHAREKEY, VTKEY 7 | import os 8 | import requests 9 | import json 10 | from time import sleep 11 | import argparse 12 | import sys 13 | import concurrent.futures 14 | 15 | def createDir(): 16 | ''' 17 | Check if we have directories to hold the samples 18 | and their subsequent categories 19 | ''' 20 | # handle the "FileExistsError" if the dir exists 21 | folders = ["./pe_file", "./elf_file", "./zip_file", "./misc"] 22 | for folder in folders: 23 | try: 24 | os.mkdir(folder) 25 | except OSError: 26 | print(f"{folder} already exists, skipping...") 27 | continue 28 | 29 | def grabHashes(): 30 | ''' 31 | query Malshare for ALL samples from last 24h 32 | ''' 33 | # initialize sha1hashes which contains ALL hashes from last 24 hrs 34 | global sha1hashes 35 | payload = {"api_key": MALSHAREKEY, "action": "getlist"} 36 | r = requests.get("https://malshare.com/api.php", params=payload) 37 | raw_hashlist = r.text 38 | loadedJSON = json.loads(raw_hashlist) 39 | sha1hashes = [hash["sha1"] for hash in loadedJSON] 40 | 41 | def downloadSamples(): 42 | ''' 43 | download specified amount of samples we just queried from Malshare 44 | ''' 45 | print(""" 46 | =========================================================== 47 | Downloading samples from Malshare, this may take a while... 48 | =========================================================== 49 | """) 50 | for hash in sha1hashes[:args.number]: 51 | payload = {"api_key": MALSHAREKEY, "action": "getfile", "hash": hash} 52 | r = requests.get("https://malshare.com/api.php", params=payload) 53 | sample = r.content 54 | with open(hash, "wb") as fh: 55 | print(f"Downloading {hash}...") 56 | fh.write(sample) 57 | 58 | def first4Bytes(file2read): 59 | ''' 60 | Returns first four hex-encoded bytes of a file 61 | ''' 62 | with open(file2read, "rb") as fd: 63 | return fd.read(4) 64 | 65 | def getKey(invalue): 66 | ''' 67 | Returns a key when given a dictionary value 68 | ''' 69 | for key, value in magicTypes.items(): 70 | if invalue == value: 71 | return key 72 | 73 | def queryVT(sampleHash): 74 | ''' 75 | query VT to see if we can get names for each sha1 hash passed to this function 76 | ''' 77 | header = {"x-apikey":VTKEY} 78 | url = f"https://www.virustotal.com/api/v3/files/{sampleHash}" 79 | vtRequest = requests.get(url, headers=header) 80 | JSONData = vtRequest.json() 81 | JSONArray.append(JSONData) 82 | 83 | def renameSamples(): 84 | ''' 85 | rename the samples if we found anything on VT 86 | ''' 87 | print(""" 88 | ============================= 89 | Attempting to name samples... 90 | ============================= 91 | """) 92 | for file in sha1hashes[:args.number]: 93 | for fileQuery in JSONArray: 94 | try: 95 | fileName = fileQuery["data"]["attributes"]["meaningful_name"] 96 | if str(file) == fileQuery["data"]["attributes"]["sha1"]: 97 | print(f"[*] {file} was identified as {fileName} ") 98 | os.replace(file, f"{fileName}") 99 | except KeyError: 100 | print(f"[*] {file} was not in VirusTotal results, not naming it...") 101 | continue 102 | 103 | def classifySamples(): 104 | ''' 105 | classify the files based on their filetype and move them 106 | to their respective folder 107 | ''' 108 | global magicTypes 109 | print(""" 110 | =================================== 111 | Classifying samples by magic bytes 112 | =================================== 113 | """) 114 | # dictionary storing our magic bytes and associated filetype 115 | magicTypes = { "pe_file": b'\x4d\x5a\x90\x00', 116 | "elf_file": b'\x7f\x45\x4c\x46', 117 | "zip_file": b'\x50\x4b\x03\x04' } 118 | # make a list containing ONLY files from current directory 119 | files = [ file for file in os.listdir(os.curdir) if os.path.isfile(file)] 120 | for file in files: 121 | if first4Bytes(file) in magicTypes.values(): 122 | print(f"{file} is a {getKey(first4Bytes(file))}") 123 | os.replace(f"./{file}", f"{getKey(first4Bytes(file))}/{file}") 124 | else: 125 | print(f"{file} is not in our magic dictionary, moving to misc/") 126 | os.replace(f"./{file}", f"misc/{file}") 127 | 128 | if __name__ == '__main__': 129 | global parser 130 | global JSONArray 131 | # all of our VT data will be stored in this array, memory be damned! 132 | JSONArray = [] 133 | parser = argparse.ArgumentParser() 134 | parser.add_argument("-n", "--number", type=int, help="number of samples to download") 135 | args = parser.parse_args() 136 | if args.number: 137 | print("[*] Creating directory structure") 138 | createDir() 139 | print("[*] Grabbing list of hashes from Malshare") 140 | grabHashes() 141 | print("[*] Looking up these hashes on VirusTotal") 142 | 143 | # slice the global variable "sha1hashes" to grab specified number 144 | for hash in sha1hashes[:args.number]: 145 | queryVT(hash) 146 | sleep(.25) # sleep to abide by VT's 4/min requests API cap 147 | 148 | # debugging print statement to make sure hashes are correct 149 | #print(f"Printing the hashes we found:\n{sha1hashes[:args.number]}") 150 | downloadSamples() 151 | renameSamples() 152 | classifySamples() 153 | 154 | with open("VTResults.json", "w") as outfile: 155 | json.dump(JSONArray, outfile) 156 | 157 | with open("sampleHashes.txt", "w") as outfile: 158 | outfile.write(str(sha1hashes[:args.number])) 159 | 160 | elif not len(sys.argv) > 1: 161 | print("Add --help for usage") 162 | 163 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------