Merge pull request #1373 from SkynetLabs/ivo/clamav

Malware scanning

changelog/items/key-updates/malware-scanner.md

@@ -0,0 +1 @@
+- Add malware scanner service, activated by adding `s` to `PORTAL_MODULES`

dc

@@ -6,7 +6,10 @@
 # information you can run `./dc` or `./dc help`.
 
 if [ -f .env ]; then
-  OLD_IFS=$IFS; IFS=$'\n'; for x in `grep -v '^#.*' .env`; do export $x; done; IFS=$OLD_IFS
+  OLD_IFS=$IFS
+  IFS=$'\n'
+  for x in $(grep -v '^#.*' .env); do export $x; done
+  IFS=$OLD_IFS
 fi
 
 # include base docker compose file
@@ -20,7 +23,7 @@ for i in $(seq 1 ${#PORTAL_MODULES}); do
 
   # blocker module - alias "b"
   if [[ ${PORTAL_MODULES:i-1:1} == "b" ]]; then
-    COMPOSE_FILES+=" -f docker-compose.blocker.yml"
+    COMPOSE_FILES+=" -f docker-compose.mongodb.yml -f docker-compose.blocker.yml"
   fi
 
   # jaeger module - alias "j"
@@ -28,7 +31,12 @@ for i in $(seq 1 ${#PORTAL_MODULES}); do
     COMPOSE_FILES+=" -f docker-compose.jaeger.yml"
   fi
 
-  # mongodb module - alias "m". implied by "a"
+  # malware-scanner module - alias "s"
+  if [[ ${PORTAL_MODULES:i-1:1} == "s" ]]; then
+    COMPOSE_FILES+=" -f docker-compose.blocker.yml -f docker-compose.mongodb.yml -f docker-compose.malware-scanner.yml"
+  fi
+
+  # mongodb module - alias "m"
   if [[ ${PORTAL_MODULES:i-1:1} == "m" ]]; then
     COMPOSE_FILES+=" -f docker-compose.mongodb.yml"
   fi

docker-compose.blocker.yml

@@ -22,7 +22,7 @@ services:
       - 4000
     networks:
       shared:
-        ipv4_address: 10.10.10.102
+        ipv4_address: 10.10.10.110
     depends_on:
       - mongo
       - sia

docker-compose.malware-scanner.yml

@@ -0,0 +1,53 @@
+version: "3.7"
+
+x-logging: &default-logging
+  driver: json-file
+  options:
+    max-size: "10m"
+    max-file: "3"
+
+services:
+
+  clamav:
+    image: clamav/clamav:stable_base
+    container_name: clamav
+    restart: on-failure
+    logging: *default-logging
+    volumes:
+      - ./docker/data/clamav/clamav/defs:/var/lib/clamav
+      - ./docker/clamav/clamd.conf:/etc/clamav/clamd.conf:ro
+    expose:
+      - 3310 # NEVER expose this outside of the local network!
+    deploy:
+      resources:
+        limits:
+          cpus: '${CLAMAV_CPU:-0.50}'
+    networks:
+      shared:
+        ipv4_address: 10.10.10.100
+
+  malware-scanner:
+    build:
+      context: ./docker/malware-scanner
+      dockerfile: Dockerfile
+      args:
+        branch: main
+    container_name: malware-scanner
+    restart: unless-stopped
+    logging: *default-logging
+    env_file:
+      - .env
+    environment:
+      - CLAMAV_IP=${CLAMAV_IP:-10.10.10.100}
+      - CLAMAV_PORT=${CLAMAV_PORT:-3310}
+      - BLOCKER_IP=${BLOCKER_IP:-10.10.10.110}
+      - BLOCKER_PORT=${BLOCKER_PORT:-4000}
+    expose:
+      - 4000
+    networks:
+      shared:
+        ipv4_address: 10.10.10.101
+    depends_on:
+      - mongo
+      - clamav
+      - blocker

docker/clamav/clamd.conf

@@ -0,0 +1,794 @@
+##
+## Example config file for the Clam AV daemon
+## Please read the clamd.conf(5) manual before editing this file.
+##
+
+
+# Comment or remove the line below.
+# Example
+
+# Uncomment this option to enable logging.
+# LogFile must be writable for the user running daemon.
+# A full path is required.
+# Default: disabled
+LogFile /var/log/clamav/clamd.log
+
+# By default the log file is locked for writing - the lock protects against
+# running clamd multiple times (if want to run another clamd, please
+# copy the configuration file, change the LogFile variable, and run
+# the daemon with --config-file option).
+# This option disables log file locking.
+# Default: no
+#LogFileUnlock yes
+
+# Maximum size of the log file.
+# Value of 0 disables the limit.
+# You may use 'M' or 'm' for megabytes (1M = 1m = 1048576 bytes)
+# and 'K' or 'k' for kilobytes (1K = 1k = 1024 bytes). To specify the size
+# in bytes just don't use modifiers. If LogFileMaxSize is enabled, log
+# rotation (the LogRotate option) will always be enabled.
+# Default: 1M
+LogFileMaxSize 50M
+
+# Log time with each message.
+# Default: no
+LogTime yes
+
+# Also log clean files. Useful in debugging but drastically increases the
+# log size.
+# Default: no
+#LogClean yes
+
+# Use system logger (can work together with LogFile).
+# Default: no
+#LogSyslog yes
+
+# Specify the type of syslog messages - please refer to 'man syslog'
+# for facility names.
+# Default: LOG_LOCAL6
+#LogFacility LOG_MAIL
+
+# Enable verbose logging.
+# Default: no
+#LogVerbose yes
+
+# Enable log rotation. Always enabled when LogFileMaxSize is enabled.
+# Default: no
+#LogRotate yes
+
+# Enable Prelude output.
+# Default: no
+#PreludeEnable yes
+#
+# Set the name of the analyzer used by prelude-admin.
+# Default: ClamAV
+#PreludeAnalyzerName ClamAV
+
+# Log additional information about the infected file, such as its
+# size and hash, together with the virus name.
+#ExtendedDetectionInfo yes
+
+# This option allows you to save a process identifier of the listening
+# daemon (main thread).
+# This file will be owned by root, as long as clamd was started by root.
+# It is recommended that the directory where this file is stored is
+# also owned by root to keep other users from tampering with it.
+# Default: disabled
+PidFile /run/lock/clamd.pid
+
+# Optional path to the global temporary directory.
+# Default: system specific (usually /tmp or /var/tmp).
+#TemporaryDirectory /var/tmp
+
+# Path to the database directory.
+# Default: hardcoded (depends on installation options)
+#DatabaseDirectory /var/lib/clamav
+
+# Only load the official signatures published by the ClamAV project.
+# Default: no
+#OfficialDatabaseOnly no
+
+# The daemon can work in local mode, network mode or both.
+# Due to security reasons we recommend the local mode.
+
+# Path to a local socket file the daemon will listen on.
+# Default: disabled (must be specified by a user)
+LocalSocket /run/clamav/clamd.sock
+
+# Sets the group ownership on the unix socket.
+# Default: disabled (the primary group of the user running clamd)
+#LocalSocketGroup virusgroup
+
+# Sets the permissions on the unix socket to the specified mode.
+# Default: disabled (socket is world accessible)
+#LocalSocketMode 660
+
+# Remove stale socket after unclean shutdown.
+# Default: yes
+#FixStaleSocket yes
+
+# TCP port address.
+# Default: no
+TCPSocket 3310
+
+# TCP address.
+# By default we bind to INADDR_ANY, probably not wise.
+# Enable the following to provide some degree of protection
+# from the outside world. This option can be specified multiple
+# times if you want to listen on multiple IPs. IPv6 is now supported.
+# Default: no
+TCPAddr 0.0.0.0
+
+# Maximum length the queue of pending connections may grow to.
+# Default: 200
+#MaxConnectionQueueLength 30
+
+# Clamd uses FTP-like protocol to receive data from remote clients.
+# If you are using clamav-milter to balance load between remote clamd daemons
+# on firewall servers you may need to tune the options below.
+
+# Close the connection when the data size limit is exceeded.
+# The value should match your MTA's limit for a maximum attachment size.
+# Default: 25M
+StreamMaxLength 100M
+
+# Limit port range.
+# Default: 1024
+#StreamMinPort 30000
+# Default: 2048
+#StreamMaxPort 32000
+
+# Maximum number of threads running at the same time.
+# Default: 10
+#MaxThreads 20
+
+# Waiting for data from a client socket will timeout after this time (seconds).
+# Default: 120
+#ReadTimeout 300
+
+# This option specifies the time (in seconds) after which clamd should
+# timeout if a client doesn't provide any initial command after connecting.
+# Default: 30
+#CommandReadTimeout 30
+
+# This option specifies how long to wait (in milliseconds) if the send buffer
+# is full.
+# Keep this value low to prevent clamd hanging.
+#
+# Default: 500
+#SendBufTimeout 200
+
+# Maximum number of queued items (including those being processed by
+# MaxThreads threads).
+# It is recommended to have this value at least twice MaxThreads if possible.
+# WARNING: you shouldn't increase this too much to avoid running out  of file
+# descriptors, the following condition should hold:
+# MaxThreads*MaxRecursion + (MaxQueue - MaxThreads) + 6< RLIMIT_NOFILE (usual
+# max is 1024).
+#
+# Default: 100
+#MaxQueue 200
+
+# Waiting for a new job will timeout after this time (seconds).
+# Default: 30
+#IdleTimeout 60
+
+# Don't scan files and directories matching regex
+# This directive can be used multiple times
+# Default: scan all
+#ExcludePath ^/proc/
+#ExcludePath ^/sys/
+
+# Maximum depth directories are scanned at.
+# Default: 15
+#MaxDirectoryRecursion 20
+
+# Follow directory symlinks.
+# Default: no
+#FollowDirectorySymlinks yes
+
+# Follow regular file symlinks.
+# Default: no
+#FollowFileSymlinks yes
+
+# Scan files and directories on other filesystems.
+# Default: yes
+#CrossFilesystems yes
+
+# Perform a database check.
+# Default: 600 (10 min)
+#SelfCheck 600
+
+# Enable non-blocking (multi-threaded/concurrent) database reloads.
+# This feature will temporarily load a second scanning engine while scanning
+# continues using the first engine. Once loaded, the new engine takes over.
+# The old engine is removed as soon as all scans using the old engine have
+# completed.
+# This feature requires more RAM, so this option is provided in case users are
+# willing to block scans during reload in exchange for lower RAM requirements.
+# Default: yes
+ConcurrentDatabaseReload no
+
+# Execute a command when virus is found. In the command string %v will
+# be replaced with the virus name and %f will be replaced with the file name.
+# Additionally, two environment variables will be defined: $CLAM_VIRUSEVENT_FILENAME
+# and $CLAM_VIRUSEVENT_VIRUSNAME.
+# Default: no
+#VirusEvent /usr/local/bin/send_sms 123456789 "VIRUS ALERT: %v in %f"
+
+# Run as another user (clamd must be started by root for this option to work)
+# Default: don't drop privileges
+User clamav
+
+# Stop daemon when libclamav reports out of memory condition.
+#ExitOnOOM yes
+
+# Don't fork into background.
+# Default: no
+#Foreground yes
+
+# Enable debug messages in libclamav.
+# Default: no
+#Debug yes
+
+# Do not remove temporary files (for debug purposes).
+# Default: no
+#LeaveTemporaryFiles yes
+
+# Permit use of the ALLMATCHSCAN command. If set to no, clamd will reject
+# any ALLMATCHSCAN command as invalid.
+# Default: yes
+#AllowAllMatchScan no
+
+# Detect Possibly Unwanted Applications.
+# Default: no
+#DetectPUA yes
+
+# Exclude a specific PUA category. This directive can be used multiple times.
+# See https://github.com/vrtadmin/clamav-faq/blob/master/faq/faq-pua.md for
+# the complete list of PUA categories.
+# Default: Load all categories (if DetectPUA is activated)
+#ExcludePUA NetTool
+#ExcludePUA PWTool
+
+# Only include a specific PUA category. This directive can be used multiple
+# times.
+# Default: Load all categories (if DetectPUA is activated)
+#IncludePUA Spy
+#IncludePUA Scanner
+#IncludePUA RAT
+
+# This option causes memory or nested map scans to dump the content to disk.
+# If you turn on this option, more data is written to disk and is available
+# when the LeaveTemporaryFiles option is enabled.
+#ForceToDisk yes
+
+# This option allows you to disable the caching feature of the engine. By
+# default, the engine will store an MD5 in a cache of any files that are
+# not flagged as virus or that hit limits checks. Disabling the cache will
+# have a negative performance impact on large scans.
+# Default: no
+#DisableCache yes
+
+# In some cases (eg. complex malware, exploits in graphic files, and others),
+# ClamAV uses special algorithms to detect abnormal patterns and behaviors that
+# may be malicious.  This option enables alerting on such heuristically
+# detected potential threats.
+# Default: yes
+#HeuristicAlerts yes
+
+# Allow heuristic alerts to take precedence.
+# When enabled, if a heuristic scan (such as phishingScan) detects
+# a possible virus/phish it will stop scan immediately. Recommended, saves CPU
+# scan-time.
+# When disabled, virus/phish detected by heuristic scans will be reported only
+# at the end of a scan. If an archive contains both a heuristically detected
+# virus/phish, and a real malware, the real malware will be reported
+#
+# Keep this disabled if you intend to handle "Heuristics.*" viruses
+# differently from "real" malware.
+# If a non-heuristically-detected virus (signature-based) is found first,
+# the scan is interrupted immediately, regardless of this config option.
+#
+# Default: no
+#HeuristicScanPrecedence yes
+
+
+##
+## Heuristic Alerts
+##
+
+# With this option clamav will try to detect broken executables (both PE and
+# ELF) and alert on them with the Broken.Executable heuristic signature.
+# Default: no
+#AlertBrokenExecutables yes
+
+# With this option clamav will try to detect broken media file (JPEG,
+# TIFF, PNG, GIF) and alert on them with a Broken.Media heuristic signature.
+# Default: no
+#AlertBrokenMedia yes
+
+# Alert on encrypted archives _and_ documents with heuristic signature
+# (encrypted .zip, .7zip, .rar, .pdf).
+# Default: no
+#AlertEncrypted yes
+
+# Alert on encrypted archives with heuristic signature (encrypted .zip, .7zip,
+# .rar).
+# Default: no
+#AlertEncryptedArchive yes
+
+# Alert on encrypted archives with heuristic signature (encrypted .pdf).
+# Default: no
+#AlertEncryptedDoc yes
+
+# With this option enabled OLE2 files containing VBA macros, which were not
+# detected by signatures will be marked as "Heuristics.OLE2.ContainsMacros".
+# Default: no
+#AlertOLE2Macros yes
+
+# Alert on SSL mismatches in URLs, even if the URL isn't in the database.
+# This can lead to false positives.
+# Default: no
+#AlertPhishingSSLMismatch yes
+
+# Alert on cloaked URLs, even if URL isn't in database.
+# This can lead to false positives.
+# Default: no
+#AlertPhishingCloak yes
+
+# Alert on raw DMG image files containing partition intersections
+# Default: no
+#AlertPartitionIntersection yes
+
+
+##
+## Executable files
+##
+
+# PE stands for Portable Executable - it's an executable file format used
+# in all 32 and 64-bit versions of Windows operating systems. This option
+# allows ClamAV to perform a deeper analysis of executable files and it's also
+# required for decompression of popular executable packers such as UPX, FSG,
+# and Petite. If you turn off this option, the original files will still be
+# scanned, but without additional processing.
+# Default: yes
+#ScanPE yes
+
+# Certain PE files contain an authenticode signature. By default, we check
+# the signature chain in the PE file against a database of trusted and
+# revoked certificates if the file being scanned is marked as a virus.
+# If any certificate in the chain validates against any trusted root, but
+# does not match any revoked certificate, the file is marked as trusted.
+# If the file does match a revoked certificate, the file is marked as virus.
+# The following setting completely turns off authenticode verification.
+# Default: no
+#DisableCertCheck yes
+
+# Executable and Linking Format is a standard format for UN*X executables.
+# This option allows you to control the scanning of ELF files.
+# If you turn off this option, the original files will still be scanned, but
+# without additional processing.
+# Default: yes
+#ScanELF yes
+
+
+##
+## Documents
+##
+
+# This option enables scanning of OLE2 files, such as Microsoft Office
+# documents and .msi files.
+# If you turn off this option, the original files will still be scanned, but
+# without additional processing.
+# Default: yes
+#ScanOLE2 yes
+
+# This option enables scanning within PDF files.
+# If you turn off this option, the original files will still be scanned, but
+# without decoding and additional processing.
+# Default: yes
+#ScanPDF yes
+
+# This option enables scanning within SWF files.
+# If you turn off this option, the original files will still be scanned, but
+# without decoding and additional processing.
+# Default: yes
+#ScanSWF yes
+
+# This option enables scanning xml-based document files supported by libclamav.
+# If you turn off this option, the original files will still be scanned, but
+# without additional processing.
+# Default: yes
+#ScanXMLDOCS yes
+
+# This option enables scanning of HWP3 files.
+# If you turn off this option, the original files will still be scanned, but
+# without additional processing.
+# Default: yes
+#ScanHWP3 yes
+
+
+##
+## Mail files
+##
+
+# Enable internal e-mail scanner.
+# If you turn off this option, the original files will still be scanned, but
+# without parsing individual messages/attachments.
+# Default: yes
+#ScanMail yes
+
+# Scan RFC1341 messages split over many emails.
+# You will need to periodically clean up $TemporaryDirectory/clamav-partial
+# directory.
+# WARNING: This option may open your system to a DoS attack.
+#	   Never use it on loaded servers.
+# Default: no
+#ScanPartialMessages yes
+
+# With this option enabled ClamAV will try to detect phishing attempts by using
+# HTML.Phishing and Email.Phishing NDB signatures.
+# Default: yes
+#PhishingSignatures no
+
+# With this option enabled ClamAV will try to detect phishing attempts by
+# analyzing URLs found in emails using WDB and PDB signature databases.
+# Default: yes
+#PhishingScanURLs no
+
+
+##
+## Data Loss Prevention (DLP)
+##
+
+# Enable the DLP module
+# Default: No
+#StructuredDataDetection yes
+
+# This option sets the lowest number of Credit Card numbers found in a file
+# to generate a detect.
+# Default: 3
+#StructuredMinCreditCardCount 5
+
+# With this option enabled the DLP module will search for valid Credit Card
+# numbers only. Debit and Private Label cards will not be searched.
+# Default: no
+#StructuredCCOnly yes
+
+# This option sets the lowest number of Social Security Numbers found
+# in a file to generate a detect.
+# Default: 3
+#StructuredMinSSNCount 5
+
+# With this option enabled the DLP module will search for valid
+# SSNs formatted as xxx-yy-zzzz
+# Default: yes
+#StructuredSSNFormatNormal yes
+
+# With this option enabled the DLP module will search for valid
+# SSNs formatted as xxxyyzzzz
+# Default: no
+#StructuredSSNFormatStripped yes
+
+
+##
+## HTML
+##
+
+# Perform HTML normalisation and decryption of MS Script Encoder code.
+# Default: yes
+# If you turn off this option, the original files will still be scanned, but
+# without additional processing.
+#ScanHTML yes
+
+
+##
+## Archives
+##
+
+# ClamAV can scan within archives and compressed files.
+# If you turn off this option, the original files will still be scanned, but
+# without unpacking and additional processing.
+# Default: yes
+#ScanArchive yes
+
+
+##
+## Limits
+##
+
+# The options below protect your system against Denial of Service attacks
+# using archive bombs.
+
+# This option sets the maximum amount of time to a scan may take.
+# In this version, this field only affects the scan time of ZIP archives.
+# Value of 0 disables the limit.
+# Note: disabling this limit or setting it too high may result allow scanning
+# of certain files to lock up the scanning process/threads resulting in a
+# Denial of Service.
+# Time is in milliseconds.
+# Default: 120000
+MaxScanTime 300000
+
+# This option sets the maximum amount of data to be scanned for each input
+# file. Archives and other containers are recursively extracted and scanned
+# up to this value.
+# Value of 0 disables the limit
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Default: 100M
+MaxScanSize 1024M
+
+# Files larger than this limit won't be scanned. Affects the input file itself
+# as well as files contained inside it (when the input file is an archive, a
+# document or some other kind of container).
+# Value of 0 disables the limit.
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Technical design limitations prevent ClamAV from scanning files greater than
+# 2 GB at this time.
+# Default: 25M
+MaxFileSize 1024M
+
+# Nested archives are scanned recursively, e.g. if a Zip archive contains a RAR
+# file, all files within it will also be scanned. This options specifies how
+# deeply the process should be continued.
+# Note: setting this limit too high may result in severe damage to the system.
+# Default: 17
+#MaxRecursion 10
+
+# Number of files to be scanned within an archive, a document, or any other
+# container file.
+# Value of 0 disables the limit.
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Default: 10000
+#MaxFiles 15000
+
+# Maximum size of a file to check for embedded PE. Files larger than this value
+# will skip the additional analysis step.
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Default: 10M
+#MaxEmbeddedPE 10M
+
+# Maximum size of a HTML file to normalize. HTML files larger than this value
+# will not be normalized or scanned.
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Default: 10M
+#MaxHTMLNormalize 10M
+
+# Maximum size of a normalized HTML file to scan. HTML files larger than this
+# value after normalization will not be scanned.
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Default: 2M
+#MaxHTMLNoTags 2M
+
+# Maximum size of a script file to normalize. Script content larger than this
+# value will not be normalized or scanned.
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Default: 5M
+#MaxScriptNormalize 5M
+
+# Maximum size of a ZIP file to reanalyze type recognition. ZIP files larger
+# than this value will skip the step to potentially reanalyze as PE.
+# Note: disabling this limit or setting it too high may result in severe damage
+# to the system.
+# Default: 1M
+#MaxZipTypeRcg 1M
+
+# This option sets the maximum number of partitions of a raw disk image to be
+# scanned.
+# Raw disk images with more partitions than this value will have up to
+# the value number partitions scanned. Negative values are not allowed.
+# Note: setting this limit too high may result in severe damage or impact
+# performance.
+# Default: 50
+#MaxPartitions 128
+
+# This option sets the maximum number of icons within a PE to be scanned.
+# PE files with more icons than this value will have up to the value number
+# icons scanned.
+# Negative values are not allowed.
+# WARNING: setting this limit too high may result in severe damage or impact
+# performance.
+# Default: 100
+#MaxIconsPE 200
+
+# This option sets the maximum recursive calls for HWP3 parsing during
+# scanning. HWP3 files using more than this limit will be terminated and
+# alert the user.
+# Scans will be unable to scan any HWP3 attachments if the recursive limit
+# is reached.
+# Negative values are not allowed.
+# WARNING: setting this limit too high may result in severe damage or impact
+# performance.
+# Default: 16
+#MaxRecHWP3 16
+
+# This option sets the maximum calls to the PCRE match function during
+# an instance of regex matching.
+# Instances using more than this limit will be terminated and alert the user
+# but the scan will continue.
+# For more information on match_limit, see the PCRE documentation.
+# Negative values are not allowed.
+# WARNING: setting this limit too high may severely impact performance.
+# Default: 100000
+#PCREMatchLimit 20000
+
+# This option sets the maximum recursive calls to the PCRE match function
+# during an instance of regex matching.
+# Instances using more than this limit will be terminated and alert the user
+# but the scan will continue.
+# For more information on match_limit_recursion, see the PCRE documentation.
+# Negative values are not allowed and values > PCREMatchLimit are superfluous.
+# WARNING: setting this limit too high may severely impact performance.
+# Default: 2000
+#PCRERecMatchLimit 10000
+
+# This option sets the maximum filesize for which PCRE subsigs will be
+# executed. Files exceeding this limit will not have PCRE subsigs executed
+# unless a subsig is encompassed to a smaller buffer.
+# Negative values are not allowed.
+# Setting this value to zero disables the limit.
+# WARNING: setting this limit too high or disabling it may severely impact
+# performance.
+# Default: 25M
+#PCREMaxFileSize 100M
+
+# When AlertExceedsMax is set, files exceeding the MaxFileSize, MaxScanSize, or
+# MaxRecursion limit will be flagged with the virus name starting with
+# "Heuristics.Limits.Exceeded".
+# Default: no
+#AlertExceedsMax yes
+
+##
+## On-access Scan Settings
+##
+
+# Don't scan files larger than OnAccessMaxFileSize
+# Value of 0 disables the limit.
+# Default: 5M
+#OnAccessMaxFileSize 10M
+
+# Max number of scanning threads to allocate to the OnAccess thread pool at
+# startup. These threads are the ones responsible for creating a connection
+# with the daemon and kicking off scanning after an event has been processed.
+# To prevent clamonacc from consuming all clamd's resources keep this lower
+# than clamd's max threads.
+# Default: 5
+#OnAccessMaxThreads 10
+
+# Max amount of time (in milliseconds) that the OnAccess client should spend
+# for every connect, send, and recieve attempt when communicating with clamd
+# via curl.
+# Default: 5000 (5 seconds)
+# OnAccessCurlTimeout 10000
+
+# Toggles dynamic directory determination. Allows for recursively watching
+# include paths.
+# Default: no
+#OnAccessDisableDDD yes
+
+# Set the include paths (all files inside them will be scanned). You can have
+# multiple OnAccessIncludePath directives but each directory must be added
+# in a separate line.
+# Default: disabled
+#OnAccessIncludePath /home
+#OnAccessIncludePath /students
+
+# Set the exclude paths. All subdirectories are also excluded.
+# Default: disabled
+#OnAccessExcludePath /home/user
+
+# Modifies fanotify blocking behaviour when handling permission events.
+# If off, fanotify will only notify if the file scanned is a virus,
+# and not perform any blocking.
+# Default: no
+#OnAccessPrevention yes
+
+# When using prevention, if this option is turned on, any errors that occur
+# during scanning will result in the event attempt being denied. This could
+# potentially lead to unwanted system behaviour with certain configurations,
+# so the client defaults this to off and prefers allowing access events in
+# case of scan or connection error.
+# Default: no
+#OnAccessDenyOnError yes
+
+# Toggles extra scanning and notifications when a file or directory is
+# created or moved.
+# Requires the  DDD system to kick-off extra scans.
+# Default: no
+#OnAccessExtraScanning yes
+
+# Set the  mount point to be scanned. The mount point specified, or the mount
+# point containing the specified directory will be watched. If any directories
+# are specified, this option will preempt (disable and ignore all options
+# related to) the DDD system. This option will result in verdicts only.
+# Note that prevention is explicitly disallowed to prevent common, fatal
+# misconfigurations. (e.g. watching "/" with prevention on and no exclusions
+# made on vital system directories)
+# It can be used multiple times.
+# Default: disabled
+#OnAccessMountPath /
+#OnAccessMountPath /home/user
+
+# With this option you can exclude the root UID (0). Processes run under
+# root with be able to access all files without triggering scans or
+# permission denied events.
+# Note that if clamd cannot check the uid of the process that generated an
+# on-access scan event (e.g., because OnAccessPrevention was not enabled, and
+# the process already exited), clamd will perform a scan.  Thus, setting
+# OnAccessExcludeRootUID is not *guaranteed* to prevent every access by the
+# root user from triggering a scan (unless OnAccessPrevention is enabled).
+# Default: no
+#OnAccessExcludeRootUID no
+
+# With this option you can exclude specific UIDs. Processes with these UIDs
+# will be able to access all files without triggering scans or permission
+# denied events.
+# This option can be used multiple times (one per line).
+# Using a value of 0 on any line will disable this option entirely.
+# To exclude the root UID (0) please enable the OnAccessExcludeRootUID
+# option.
+# Also note that if clamd cannot check the uid of the process that generated an
+# on-access scan event (e.g., because OnAccessPrevention was not enabled, and
+# the process already exited), clamd will perform a scan.  Thus, setting
+# OnAccessExcludeUID is not *guaranteed* to prevent every access by the
+# specified uid from triggering a scan (unless OnAccessPrevention is enabled).
+# Default: disabled
+#OnAccessExcludeUID -1
+
+# This option allows exclusions via user names when using the on-access
+# scanning client. It can be used multiple times.
+# It has the same potential race condition limitations of the
+# OnAccessExcludeUID option.
+# Default: disabled
+#OnAccessExcludeUname clamav
+
+# Number of times the OnAccess client will retry a failed scan due to
+# connection problems (or other issues).
+# Default: 0
+#OnAccessRetryAttempts 3
+
+##
+## Bytecode
+##
+
+# With this option enabled ClamAV will load bytecode from the database.
+# It is highly recommended you keep this option on, otherwise you'll miss
+# detections for many new viruses.
+# Default: yes
+#Bytecode yes
+
+# Set bytecode security level.
+# Possible values:
+#   None -      No security at all, meant for debugging.
+#               DO NOT USE THIS ON PRODUCTION SYSTEMS.
+#               This value is only available if clamav was built
+#               with --enable-debug!
+#   TrustSigned - Trust bytecode loaded from signed .c[lv]d files, insert
+#               runtime safety checks for bytecode loaded from other sources.
+#   Paranoid -  Don't trust any bytecode, insert runtime checks for all.
+# Recommended: TrustSigned, because bytecode in .cvd files already has these
+# checks.
+# Note that by default only signed bytecode is loaded, currently you can only
+# load unsigned bytecode in --enable-debug mode.
+#
+# Default: TrustSigned
+#BytecodeSecurity TrustSigned
+
+# Allow loading bytecode from outside digitally signed .c[lv]d files.
+# **Caution**: You should NEVER run bytecode signatures from untrusted sources.
+# Doing so may result in arbitrary code execution.
+# Default: no
+#BytecodeUnsigned yes
+
+# Set bytecode timeout in milliseconds.
+#
+# Default: 5000
+# BytecodeTimeout 1000

docker/malware-scanner/Dockerfile

@@ -0,0 +1,23 @@
+FROM golang:1.17.3
+LABEL maintainer="SkynetLabs <devs@siasky.net>"
+
+ENV GOOS linux
+ENV GOARCH amd64
+
+ARG branch=main
+
+WORKDIR /root
+
+RUN git clone --single-branch --branch ${branch} https://github.com/SkynetLabs/malware-scanner.git && \
+    cd malware-scanner && \
+    go mod download && \
+    make release
+
+ENV SKYNET_DB_HOST="localhost"
+ENV SKYNET_DB_PORT="27017"
+ENV SKYNET_DB_USER="username"
+ENV SKYNET_DB_PASS="password"
+ENV CLAMAV_IP=127.0.0.1
+ENV CLAMAV_PORT=3310
+
+ENTRYPOINT ["malware-scanner"]

docker/nginx/conf.d/include/track-download

@@ -14,14 +14,35 @@ log_by_lua_block {
             method = "POST",
             headers = { ["Cookie"] = "skynet-jwt=" .. jwt },
         })
-        
+
         if err or (res and res.status ~= ngx.HTTP_NO_CONTENT) then
             ngx.log(ngx.ERR, "Failed accounts service request /track/download/" .. skylink .. ": ", err or ("[HTTP " .. res.status .. "] " .. res.body))
         end
     end
 
+    local function scan(premature, skylink, jwt)
+        if premature then return end
+
+        local httpc = require("resty.http").new()
+
+        -- 10.10.10.101 points to malware-scanner service (alias not available when using resty-http)
+        local res, err = httpc:request_uri("http://10.10.10.101:3000/scan/" .. skylink, {
+            method = "POST",
+            headers = { ["Cookie"] = "skynet-jwt=" .. jwt },
+        })
+
+        if err or (res and res.status ~= ngx.HTTP_OK) then
+            ngx.log(ngx.ERR, "Failed malware-scanner request /scan/" .. skylink .. ": ", err or ("[HTTP " .. res.status .. "] " .. res.body))
+        end
+    end
+
     if ngx.header["Skynet-Skylink"] and ngx.var.skynet_jwt ~= "" and ngx.status >= ngx.HTTP_OK and ngx.status < ngx.HTTP_SPECIAL_RESPONSE then
         local ok, err = ngx.timer.at(0, track, ngx.header["Skynet-Skylink"], ngx.status, ngx.var.body_bytes_sent, ngx.var.skynet_jwt)
         if err then ngx.log(ngx.ERR, "Failed to create timer: ", err) end
     end
+
+    -- Unlike accounts, malware-scanner wants to be pinged about each skylink,
+    -- not only the ones downloaded by registered accounts.
+    local scan_ok, scan_err = ngx.timer.at(0, scan, ngx.header["Skynet-Skylink"], ngx.var.skynet_jwt)
+    if scan_err then ngx.log(ngx.ERR, "Failed to create timer: ", scan_err) end
 }

docker/nginx/conf.d/include/track-upload

@@ -13,14 +13,35 @@ log_by_lua_block {
             method = "POST",
             headers = { ["Cookie"] = "skynet-jwt=" .. jwt },
         })
-        
+
         if err or (res and res.status ~= ngx.HTTP_NO_CONTENT) then
             ngx.log(ngx.ERR, "Failed accounts service request /track/upload/" .. skylink .. ": ", err or ("[HTTP " .. res.status .. "] " .. res.body))
         end
     end
 
+    local function scan(premature, skylink, jwt)
+        if premature then return end
+
+        local httpc = require("resty.http").new()
+
+        -- 10.10.10.101 points to malware-scanner service (alias not available when using resty-http)
+        local res, err = httpc:request_uri("http://10.10.10.101:3000/scan/" .. skylink, {
+            method = "POST",
+            headers = { ["Cookie"] = "skynet-jwt=" .. jwt },
+        })
+
+        if err or (res and res.status ~= ngx.HTTP_OK) then
+            ngx.log(ngx.ERR, "Failed malware-scanner request /scan/" .. skylink .. ": ", err or ("[HTTP " .. res.status .. "] " .. res.body))
+        end
+    end
+
     if ngx.header["Skynet-Skylink"] and ngx.var.skynet_jwt ~= "" then
         local ok, err = ngx.timer.at(0, track, ngx.header["Skynet-Skylink"], ngx.var.skynet_jwt)
         if err then ngx.log(ngx.ERR, "Failed to create timer: ", err) end
     end
+
+    -- Unlike accounts, malware-scanner wants to be pinged about each skylink,
+    -- not only the ones uploaded by registered accounts.
+    local scan_ok, scan_err = ngx.timer.at(0, scan, ngx.header["Skynet-Skylink"], ngx.var.skynet_jwt)
+    if scan_err then ngx.log(ngx.ERR, "Failed to create timer: ", scan_err) end
 }

docker/nginx/conf.d/server/server.api

@@ -76,7 +76,7 @@ location /serverload {
     # Define root directory in the nginx container to load file from
     root /usr/local/share;
 
-    # including this because of peer pressure from the other routes 
+    # including this because of peer pressure from the other routes
     include /etc/nginx/conf.d/include/cors;
 
     # tell nginx to expect json
@@ -120,7 +120,7 @@ location /abuse/ {
         return 204;
     }
 
-    proxy_pass http://10.10.10.102:4000/;
+    proxy_pass http://10.10.10.110:4000/;
 }
 
 location /report-abuse {