The Infection Monkey is a security tool which tests your Data Center's ability to withstand perimeter breaches and internal server infection. It uses various methods to propagate through a data center, and reports its success to a centralized C&C server.
The monkey is the tool which infects other machines and propagates to them, while the C&C server collects all Monkey reports and displays them to the user.
For off the shelf use, download our pre-compiled binaries from our website, to setup the C&C server follow the instructions in [Monkey Island readme](monkey_island/readme.txt). If you with to compile the binaries yourself, follow the build instructions later on in this readme.
### Initial configuration.
Whether by downloading or building from source, the Infection Monkey is basically 4 executable files for different platforms and a default configuration file.
1. By default, the monkey uses a local configuration file (usually, config.bin). This configuration file must include the address of the Monkey's C&C server.
2. After successfully connecting to the C&C server, the monkey downloads a new configuration from the server and discards the local configuration. It is possible to change the default configuration from the C&C server's UI.
In both cases the command server hostname should be modified to point at your local instance of the Monkey Island (note this doesn't require connectivity right off the bat). In addition, to improve the Monkey's chances of spreading, you can pre-seed it with credentials and usernames commonly used.
Running the C&C Server is as simple as installing our infected monkey debian package on a specific server. The initial infected machine doesn not require a direct link to this server.
Once configured, run the monkey using ```./monkey-linux-64 m0nk3y -c config.bin -s 41.50.73.31:5000``` (Windows is identical). This can be done at multiple points in the network at once.
1. Wakeup connection to c&c, sends basic info of the current machine and the configuration the monkey uses to the c&c.
1. First try direct connection to c&c.
2. If direct connection fails, try connection through a tunnel, a tunnel is found according to specified parameter (the default tunnel) or by sending a multicast query and waiting for another monkey to answer.
3. If no connection can be made to c&c, continue without it.
2. If a firewall app is running on the machine (supports Windows Firewall for Win XP and Windows Advanced Firewall for Win 7+), try to add a rule to allow all our traffic.
3. Startup of tunnel for other monkeys (if connection to c&c works).
1. firewall is checked to allow listening sockets (if we failed to add a rule to windows firewall for example, the tunnel will not be created)
2. will answer multicast requests from other monkeys in search of a tunnel.
4. Running exploitation sessions, will run x sessions according to configuration:
1. Connect to c&c and get the latest configuration
2. Scan ip ranges according to configuration.
3. Try fingerprinting each host that answer, using the classes defined in the configuration (SMBFinger, SSHFinger, etc)
4. Try exploitation on each host found, for each exploit class in configuration:
1. check exploit class supports target host (can be disabled by configuration)
2. each exploitation class will use the data acquired in fingerprinting, or during the exploit, to find the suitable monkey executable for the host from the c&c.
1. If c&c connection fails, and the source monkey’s executable is suitable, we use it.
2. If a suitable executable isn’t found, exploitation will fail.
3. Executables are cached in memory.
5. will skip hosts that are already exploited in next run
6. will skip hosts that failed during exploitation in next run (can be disabled by configuration)
5. Close tunnel before exiting
Wait for monkeys using the tunnel to unregister for it
Cleanup
Remove firewall rules if added
Configuration Options
---------------------
Key | Type | Description | Possible Values
--- | ---- | ----------- | ---------------
singleton_mutex_name | string | string of the mutex name for single instance | example: {2384ec59-0df8-4ab9-918c-843740924a28}
retry_failed_explotation | bool | sets whether or not to retry failed hosts on next scan
range_class | class name | sets which ip ranges class is used to construct the list of ips to scan | `FixedRange` - scan list is a static ips list, `RelativeRange` - scan list will be constructed according to ip address of the machine and size of the scan, `ClassCRange` - will scan the entire class c the machine is in.
scanner_class | class name | sets which scan class to use when scanning for hosts to exploit | `TCPScanner` - searches for hosts according to open tcp ports, `PingScanner` - searches for hosts according to ping scan
finger_classes | tuple of class names | sets which fingerprinting classes to use | in the list: `SMBFinger` - get host os info by checking smb info, `SSHFinger` - get host os info by checking ssh banner, `PingScanner` - get host os type by checking ping ttl. For example: `(SMBFinger, SSHFinger, PingScanner)`
skip_exploit_if_file_exist | bool | sets whether or not to abort exploit if the monkey already exists in target, used by SmbExploiter
rdp_use_vbs_download | bool | sets whether to use vbs payload for rdp exploitation in RdpExploiter. If false, bits payload is used (will fail if bitsadmin.exe doesn’t exist)
ms08_067_exploit_attempt | int | number of times to try and exploit using ms08_067 exploit
If you want to build the monkey from source and not use our provided packages, look at the readme files under [chaos_monkey](chaos_monkey) and [monkey_island](monkey_island).
