New VMRay modules (#299)

New VMRay modules
pull/302/head
Steve Clement 2019-05-02 11:52:28 +09:00 committed by GitHub
commit e8ff7c4c38
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 260 additions and 194 deletions

View File

@ -3,10 +3,12 @@
''' '''
Submit sample to VMRay. Submit sample to VMRay.
Submit a sample to VMRay Requires "vmray_rest_api"
TODO: The expansion module vmray_submit and import module vmray_import are a two step
# Deal with archive submissions process to import data from VMRay.
You can automate this by setting the PyMISP example script 'vmray_automation'
as a cron job
''' '''
@ -129,13 +131,13 @@ def vmrayProcess(vmraydata):
# Result received? # Result received?
if submissions and jobs: if submissions and jobs:
r = {'results': []} r = {'results': []}
r["results"].append({"types": "md5", "values": submissions["submission_sample_md5"]}) r['results'].append({'types': 'md5', 'values': submissions['submission_sample_md5']})
r["results"].append({"types": "sha1", "values": submissions["submission_sample_sha1"]}) r['results'].append({'types': 'sha1', 'values': submissions['submission_sample_sha1']})
r["results"].append({"types": "sha256", "values": submissions["submission_sample_sha256"]}) r['results'].append({'types': 'sha256', 'values': submissions['submission_sample_sha256']})
r["results"].append({"types": "text", "values": "VMRay Sample ID: %s" % submissions["submission_sample_id"]}) r['results'].append({'types': 'text', 'values': 'VMRay Sample ID: %s' % submissions['submission_sample_id'], 'tags': 'workflow:state="incomplete"'})
r["results"].append({"types": "text", "values": "VMRay Submission ID: %s" % submissions["submission_id"]}) r['results'].append({'types': 'text', 'values': 'VMRay Submission ID: %s' % submissions['submission_id']})
r["results"].append({"types": "text", "values": "VMRay Submission Sample IP: %s" % submissions["submission_ip_ip"]}) r['results'].append({'types': 'text', 'values': 'VMRay Submission Sample IP: %s' % submissions['submission_ip_ip']})
r["results"].append({"types": "link", "values": submissions["submission_webif_url"]}) r['results'].append({'types': 'link', 'values': submissions['submission_webif_url']})
# Include data from different jobs # Include data from different jobs
if include_vmrayjobids: if include_vmrayjobids:

View File

@ -8,68 +8,62 @@ This version supports import from different analyze jobs, starting from one samp
Requires "vmray_rest_api" Requires "vmray_rest_api"
TODO: The expansion module vmray_submit and import module vmray_import are a two step
# Import one job (analyze_id) process to import data from VMRay.
# Import STIX package (XML version) You can automate this by setting the PyMISP example script 'vmray_automation'
as a cron job
''' '''
import json import json
import re
from ._vmray.vmray_rest_api import VMRayRESTAPI from ._vmray.vmray_rest_api import VMRayRESTAPI
misperrors = {'error': 'Error'} misperrors = {'error': 'Error'}
inputSource = [] inputSource = []
moduleinfo = {'version': '0.1', 'author': 'Koen Van Impe', moduleinfo = {'version': '0.2', 'author': 'Koen Van Impe',
'description': 'Import VMRay (VTI) results', 'description': 'Import VMRay results',
'module-type': ['import']} 'module-type': ['import']}
userConfig = {'include_textdescr': {'type': 'Boolean', userConfig = {'include_analysisid': {'type': 'Boolean',
'message': 'Include textual description' 'message': 'Include link to VMRay analysis'
},
'include_analysisid': {'type': 'Boolean',
'message': 'Include VMRay analysis_id text'
}, },
'only_network_info': {'type': 'Boolean', 'include_analysisdetails': {'type': 'Boolean',
'message': 'Only include network (src-ip, hostname, domain, ...) information' 'message': 'Include (textual) analysis details'
}, },
'include_vtidetails': {'type': 'Boolean',
'message': 'Include VMRay Threat Identifier (VTI) rules'
},
'include_imphash_ssdeep': {'type': 'Boolean',
'message': 'Include imphash and ssdeep'
},
'include_extracted_files': {'type': 'Boolean',
'message': 'Include extracted files section'
},
'sample_id': {'type': 'Integer', 'sample_id': {'type': 'Integer',
'errorMessage': 'Expected a sample ID', 'errorMessage': 'Expected a sample ID',
'message': 'The VMRay sample_id' 'message': 'The VMRay sample_id'
} }
} }
moduleconfig = ['apikey', 'url'] moduleconfig = ['apikey', 'url', 'wait_period']
include_textdescr = False
include_analysisid = False
only_network_info = False
def handler(q=False): def handler(q=False):
global include_textdescr global include_analysisid, include_imphash_ssdeep, include_extracted_files, include_analysisdetails, include_vtidetails, include_static_to_ids
global include_analysisid
global only_network_info
if q is False: if q is False:
return False return False
request = json.loads(q) request = json.loads(q)
include_textdescr = request["config"].get("include_textdescr") include_analysisid = bool(int(request["config"].get("include_analysisid")))
include_analysisid = request["config"].get("include_analysisid") include_imphash_ssdeep = bool(int(request["config"].get("include_imphash_ssdeep")))
only_network_info = request["config"].get("only_network_info") include_extracted_files = bool(int(request["config"].get("include_extracted_files")))
if include_textdescr == "1": include_analysisdetails = bool(int(request["config"].get("include_extracted_files")))
include_textdescr = True include_vtidetails = bool(int(request["config"].get("include_vtidetails")))
else: include_static_to_ids = True
include_textdescr = False
if include_analysisid == "1": # print("include_analysisid: %s include_imphash_ssdeep: %s include_extracted_files: %s include_analysisdetails: %s include_vtidetails: %s" % ( include_analysisid, include_imphash_ssdeep, include_extracted_files, include_analysisdetails, include_vtidetails))
include_analysisid = True
else:
include_analysisid = False
if only_network_info == "1":
only_network_info = True
else:
only_network_info = False
sample_id = int(request["config"].get("sample_id")) sample_id = int(request["config"].get("sample_id"))
@ -81,34 +75,52 @@ def handler(q=False):
try: try:
api = VMRayRESTAPI(request["config"].get("url"), request["config"].get("apikey"), False) api = VMRayRESTAPI(request["config"].get("url"), request["config"].get("apikey"), False)
vmray_results = {'results': []} vmray_results = {'results': []}
# Get all information on the sample, returns a set of finished analyze jobs # Get all information on the sample, returns a set of finished analyze jobs
data = vmrayGetInfoAnalysis(api, sample_id) data = vmrayGetInfoAnalysis(api, sample_id)
if data["data"]: if data["data"]:
vti_patterns_found = False
for analysis in data["data"]: for analysis in data["data"]:
analysis_id = analysis["analysis_id"] analysis_id = int(analysis["analysis_id"])
if analysis_id > 0: if analysis_id > 0:
# Get the details for an analyze job # Get the details for an analyze job
analysis_data = vmrayDownloadAnalysis(api, analysis_id) analysis_data = vmrayDownloadAnalysis(api, analysis_id)
if analysis_data: if analysis_data:
if "analysis_vti_patterns" in analysis_data: if include_analysisdetails and "analysis_details" in analysis_data:
p = vmrayVtiPatterns(analysis_data["analysis_vti_patterns"]) analysis_details = vmrayAnalysisDetails(analysis_data["analysis_details"], analysis_id)
else: if analysis_details and len(analysis_details["results"]) > 0:
p = vmrayVtiPatterns(analysis_data["vti_patterns"]) vmray_results = {'results': vmray_results["results"] + analysis_details["results"]}
if p and len(p["results"]) > 0:
vti_patterns_found = True if "classifications" in analysis_data:
vmray_results = {'results': vmray_results["results"] + p["results"]} classifications = vmrayClassifications(analysis_data["classifications"], analysis_id)
if classifications and len(classifications["results"]) > 0:
vmray_results = {'results': vmray_results["results"] + classifications["results"]}
if include_extracted_files and "extracted_files" in analysis_data:
extracted_files = vmrayExtractedfiles(analysis_data["extracted_files"])
if extracted_files and len(extracted_files["results"]) > 0:
vmray_results = {'results': vmray_results["results"] + extracted_files["results"]}
if include_vtidetails and "vti" in analysis_data:
vti = vmrayVti(analysis_data["vti"])
if vti and len(vti["results"]) > 0:
vmray_results = {'results': vmray_results["results"] + vti["results"]}
if "artifacts" in analysis_data:
artifacts = vmrayArtifacts(analysis_data["artifacts"])
if artifacts and len(artifacts["results"]) > 0:
vmray_results = {'results': vmray_results["results"] + artifacts["results"]}
if include_analysisid: if include_analysisid:
a_id = {'results': []} a_id = {'results': []}
url1 = "https://cloud.vmray.com/user/analysis/view?from_sample_id=%u" % sample_id url1 = request["config"].get("url") + "/user/analysis/view?from_sample_id=%u" % sample_id
url2 = "&id=%u" % analysis_id url2 = "&id=%u" % analysis_id
url3 = "&sub=%2Freport%2Foverview.html" url3 = "&sub=%2Freport%2Foverview.html"
a_id["results"].append({"values": url1 + url2 + url3, "types": "link"}) a_id["results"].append({"values": url1 + url2 + url3, "types": "link"})
vmray_results = {'results': vmray_results["results"] + a_id["results"]} vmray_results = {'results': vmray_results["results"] + a_id["results"]}
# Clean up (remove doubles) # Clean up (remove doubles)
if vti_patterns_found: if len(vmray_results["results"]) > 0:
vmray_results = vmrayCleanup(vmray_results) vmray_results = vmrayCleanup(vmray_results)
return vmray_results return vmray_results
else: else:
@ -117,8 +129,8 @@ def handler(q=False):
else: else:
misperrors['error'] = "Unable to fetch sample id %u" % (sample_id) misperrors['error'] = "Unable to fetch sample id %u" % (sample_id)
return misperrors return misperrors
except Exception: except Exception as e: # noqa
misperrors['error'] = "Unable to access VMRay API" misperrors['error'] = "Unable to access VMRay API : %s" % (e)
return misperrors return misperrors
else: else:
misperrors['error'] = "Not a valid sample id" misperrors['error'] = "Not a valid sample id"
@ -158,80 +170,209 @@ def vmrayGetInfoAnalysis(api, sample_id):
def vmrayDownloadAnalysis(api, analysis_id): def vmrayDownloadAnalysis(api, analysis_id):
''' Get the details from an analysis''' ''' Get the details from an analysis'''
if analysis_id: if analysis_id:
data = api.call("GET", "/rest/analysis/%u/archive/additional/vti_result.json" % (analysis_id), raw_data=True) try:
return json.loads(data.read().decode()) data = api.call("GET", "/rest/analysis/%u/archive/logs/summary.json" % (analysis_id), raw_data=True)
return json.loads(data.read().decode())
except Exception as e: # noqa
misperrors['error'] = "Unable to download summary.json for analysis %s" % (analysis_id)
return misperrors
else: else:
return False return False
def vmrayVtiPatterns(vti_patterns): def vmrayVti(vti):
''' Match the VTI patterns to MISP data''' '''VMRay Threat Identifier (VTI) rules that matched for this analysis'''
if vti_patterns: if vti:
r = {'results': []}
for rule in vti:
if rule == "vti_rule_matches":
vti_rule = vti["vti_rule_matches"]
for el in vti_rule:
if "operation_desc" in el:
comment = ""
types = ["text"]
values = el["operation_desc"]
r['results'].append({'types': types, 'values': values, 'comment': comment})
return r
else:
return False
def vmrayExtractedfiles(extracted_files):
''' Information about files which were extracted during the analysis, such as files that were created, modified, or embedded by the malware'''
if extracted_files:
r = {'results': []}
for file in extracted_files:
if "file_type" and "norm_filename" in file:
comment = "%s - %s" % (file["file_type"], file["norm_filename"])
else:
comment = ""
if "norm_filename" in file:
attr_filename_c = file["norm_filename"].rsplit("\\", 1)
if len(attr_filename_c) > 1:
attr_filename = attr_filename_c[len(attr_filename_c) - 1]
else:
attr_filename = "vmray_sample"
else:
attr_filename = "vmray_sample"
if "md5_hash" in file and file["md5_hash"] is not None:
r['results'].append({'types': ["filename|md5"], 'values': '{}|{}'.format(attr_filename, file["md5_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
if include_imphash_ssdeep and "imp_hash" in file and file["imp_hash"] is not None:
r['results'].append({'types': ["filename|imphash"], 'values': '{}|{}'.format(attr_filename, file["imp_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
if "sha1_hash" in file and file["sha1_hash"] is not None:
r['results'].append({'types': ["filename|sha1"], 'values': '{}|{}'.format(attr_filename, file["sha1_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
if "sha256_hash" in file and file["sha256_hash"] is not None:
r['results'].append({'types': ["filename|sha256"], 'values': '{}|{}'.format(attr_filename, file["sha256_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
if include_imphash_ssdeep and "ssdeep_hash" in file and file["ssdeep_hash"] is not None:
r['results'].append({'types': ["filename|ssdeep"], 'values': '{}|{}'.format(attr_filename, file["ssdeep_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
return r
else:
return False
def vmrayClassifications(classification, analysis_id):
''' List the classifications, tag them on a "text" attribute '''
if classification:
r = {'results': []}
types = ["text"]
comment = ""
values = "Classification : %s " % (", ".join(str(x) for x in classification))
r['results'].append({'types': types, 'values': values, 'comment': comment})
return r
else:
return False
def vmrayAnalysisDetails(details, analysis_id):
''' General information about the analysis information '''
if details:
r = {'results': []}
types = ["text"]
comment = ""
if "execution_successful" in details:
values = "Analysis %s : execution_successful : %s " % (analysis_id, str(details["execution_successful"]))
r['results'].append({'types': types, 'values': values, 'comment': comment})
if "termination_reason" in details:
values = "Analysis %s : termination_reason : %s " % (analysis_id, str(details["termination_reason"]))
r['results'].append({'types': types, 'values': values, 'comment': comment})
if "result_str" in details:
values = "Analysis %s : result : %s " % (analysis_id, details["result_str"])
r['results'].append({'types': types, 'values': values, 'comment': comment})
return r
else:
return False
def vmrayArtifacts(patterns):
''' IOCs that were seen during the analysis '''
if patterns:
r = {'results': []} r = {'results': []}
y = {'results': []} y = {'results': []}
for pattern in vti_patterns: for pattern in patterns:
content = False if pattern == "domains":
if pattern["category"] == "_network" and pattern["operation"] == "_download_data": for el in patterns[pattern]:
content = vmrayGeneric(pattern, "url", 1) values = el["domain"]
elif pattern["category"] == "_network" and pattern["operation"] == "_connect": types = ["domain", "hostname"]
content = vmrayConnect(pattern) if "sources" in el:
elif pattern["category"] == "_network" and pattern["operation"] == "_install_server": sources = el["sources"]
content = vmrayGeneric(pattern) comment = "Found in: " + ", ".join(str(x) for x in sources)
else:
comment = ""
r['results'].append({'types': types, 'values': values, 'comment': comment, 'to_ids': include_static_to_ids})
if pattern == "files":
for el in patterns[pattern]:
filename_values = el["filename"]
attr_filename_c = filename_values.rsplit("\\", 1)
if len(attr_filename_c) > 1:
attr_filename = attr_filename_c[len(attr_filename_c) - 1]
else:
attr_filename = ""
filename_types = ["filename"]
filename_operations = el["operations"]
comment = "File operations: " + ", ".join(str(x) for x in filename_operations)
r['results'].append({'types': filename_types, 'values': filename_values, 'comment': comment})
elif only_network_info is False and pattern["category"] == "_process" and pattern["operation"] == "_alloc_wx_page": # Run through all hashes
content = vmrayGeneric(pattern) if "hashes" in el:
elif only_network_info is False and pattern["category"] == "_process" and pattern["operation"] == "_install_ipc_endpoint": for hash in el["hashes"]:
content = vmrayGeneric(pattern, "mutex", 1) if "md5_hash" in hash and hash["md5_hash"] is not None:
elif only_network_info is False and pattern["category"] == "_process" and pattern["operation"] == "_crashed_process": r['results'].append({'types': ["filename|md5"], 'values': '{}|{}'.format(attr_filename, hash["md5_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
content = vmrayGeneric(pattern) if include_imphash_ssdeep and "imp_hash" in hash and hash["imp_hash"] is not None:
elif only_network_info is False and pattern["category"] == "_process" and pattern["operation"] == "_read_from_remote_process": r['results'].append({'types': ["filename|imphash"], 'values': '{}|{}'.format(attr_filename, hash["imp_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
content = vmrayGeneric(pattern) if "sha1_hash" in hash and hash["sha1_hash"] is not None:
elif only_network_info is False and pattern["category"] == "_process" and pattern["operation"] == "_create_process_with_hidden_window": r['results'].append({'types': ["filename|sha1"], 'values': '{}|{}'.format(attr_filename, hash["sha1_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
content = vmrayGeneric(pattern) if "sha256_hash" in hash and hash["sha256_hash"] is not None:
r['results'].append({'types': ["filename|sha256"], 'values': '{}|{}'.format(attr_filename, hash["sha256_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
if include_imphash_ssdeep and "ssdeep_hash" in hash and hash["ssdeep_hash"] is not None:
r['results'].append({'types': ["filename|ssdeep"], 'values': '{}|{}'.format(attr_filename, hash["ssdeep_hash"]), 'comment': comment, 'categories': ['Payload delivery', 'Artifacts dropped'], 'to_ids': include_static_to_ids})
if pattern == "ips":
for el in patterns[pattern]:
values = el["ip_address"]
types = ["ip-dst"]
if "sources" in el:
sources = el["sources"]
comment = "Found in: " + ", ".join(str(x) for x in sources)
else:
comment = ""
elif only_network_info is False and pattern["category"] == "_anti_analysis" and pattern["operation"] == "_delay_execution": r['results'].append({'types': types, 'values': values, 'comment': comment, 'to_ids': include_static_to_ids})
content = vmrayGeneric(pattern) if pattern == "mutexes":
elif only_network_info is False and pattern["category"] == "_anti_analysis" and pattern["operation"] == "_dynamic_api_usage": for el in patterns[pattern]:
content = vmrayGeneric(pattern) values = el["mutex_name"]
types = ["mutex"]
if "sources" in el:
sources = el["operations"]
comment = "Operations: " + ", ".join(str(x) for x in sources)
else:
comment = ""
elif only_network_info is False and pattern["category"] == "_static" and pattern["operation"] == "_drop_pe_file": r['results'].append({'types': types, 'values': values, 'comment': comment, 'to_ids': include_static_to_ids})
content = vmrayGeneric(pattern, "filename", 1) if pattern == "registry":
elif only_network_info is False and pattern["category"] == "_static" and pattern["operation"] == "_execute_dropped_pe_file": for el in patterns[pattern]:
content = vmrayGeneric(pattern, "filename", 1) values = el["reg_key_name"]
types = ["regkey"]
if "sources" in el:
sources = el["operations"]
comment = "Operations: " + ", ".join(str(x) for x in sources)
else:
comment = ""
elif only_network_info is False and pattern["category"] == "_injection" and pattern["operation"] == "_modify_memory": r['results'].append({'types': types, 'values': values, 'comment': comment, 'to_ids': include_static_to_ids})
content = vmrayGeneric(pattern) if pattern == "urls":
elif only_network_info is False and pattern["category"] == "_injection" and pattern["operation"] == "_modify_memory_system": for el in patterns[pattern]:
content = vmrayGeneric(pattern) values = el["url"]
elif only_network_info is False and pattern["category"] == "_injection" and pattern["operation"] == "_modify_memory_non_system": types = ["url"]
content = vmrayGeneric(pattern) if "sources" in el:
elif only_network_info is False and pattern["category"] == "_injection" and pattern["operation"] == "_modify_control_flow": sources = el["operations"]
content = vmrayGeneric(pattern) comment = "Operations: " + ", ".join(str(x) for x in sources)
elif only_network_info is False and pattern["category"] == "_injection" and pattern["operation"] == "_modify_control_flow_non_system": else:
content = vmrayGeneric(pattern) comment = ""
elif only_network_info is False and pattern["category"] == "_file_system" and pattern["operation"] == "_create_many_files":
content = vmrayGeneric(pattern)
elif only_network_info is False and pattern["category"] == "_hide_tracks" and pattern["operation"] == "_hide_data_in_registry": r['results'].append({'types': types, 'values': values, 'comment': comment, 'to_ids': include_static_to_ids})
content = vmrayGeneric(pattern, "regkey", 1)
elif only_network_info is False and pattern["category"] == "_persistence" and pattern["operation"] == "_install_startup_script": # Remove doubles
content = vmrayGeneric(pattern, "regkey", 1)
elif only_network_info is False and pattern["category"] == "_os" and pattern["operation"] == "_enable_process_privileges":
content = vmrayGeneric(pattern)
if content:
r["results"].append(content["attributes"])
r["results"].append(content["text"])
# Remove empty results
r["results"] = [x for x in r["results"] if isinstance(x, dict) and len(x["values"]) != 0]
for el in r["results"]: for el in r["results"]:
if el not in y["results"]: if el not in y["results"]:
y["results"].append(el) y["results"].append(el)
return y return y
else: else:
return False return False
@ -239,84 +380,7 @@ def vmrayVtiPatterns(vti_patterns):
def vmrayCleanup(x): def vmrayCleanup(x):
''' Remove doubles''' ''' Remove doubles'''
y = {'results': []} y = {'results': []}
for el in x["results"]: for el in x["results"]:
if el not in y["results"]: if el not in y["results"]:
y["results"].append(el) y["results"].append(el)
return y return y
def vmraySanitizeInput(s):
''' Sanitize some input so it gets properly imported in MISP'''
if s:
s = s.replace('"', '')
s = re.sub('\\\\', r'\\', s)
return s
else:
return False
def vmrayGeneric(el, attr="", attrpos=1):
''' Convert a 'generic' VTI pattern to MISP data'''
r = {"values": []}
f = {"values": []}
if el:
content = el["technique_desc"]
if content:
if attr:
# Some elements are put between \"\" ; replace them to single
content = content.replace("\"\"", "\"")
content_split = content.split("\"")
# Attributes are between open " and close "; so use >
if len(content_split) > attrpos:
content_split[attrpos] = vmraySanitizeInput(content_split[attrpos])
r["values"].append(content_split[attrpos])
r["types"] = [attr]
# Adding the value also as text to get the extra description,
# but this is pretty useless for "url"
if include_textdescr and attr != "url":
f["values"].append(vmraySanitizeInput(content))
f["types"] = ["text"]
return {"text": f, "attributes": r}
else:
return False
else:
return False
def vmrayConnect(el):
''' Extension of vmrayGeneric , parse network connect data'''
ipre = re.compile("([0-9]{1,3}.){3}[0-9]{1,3}")
r = {"values": []}
f = {"values": []}
if el:
content = el["technique_desc"]
if content:
target = content.split("\"")
# port = (target[1].split(":"))[1] ## FIXME: not used
host = (target[1].split(":"))[0]
if ipre.match(str(host)):
r["values"].append(host)
r["types"] = ["ip-dst"]
else:
r["values"].append(host)
r["types"] = ["domain", "hostname"]
f["values"].append(vmraySanitizeInput(target[1]))
f["types"] = ["text"]
if include_textdescr:
f["values"].append(vmraySanitizeInput(content))
f["types"] = ["text"]
return {"text": f, "attributes": r}
else:
return False
else:
return False