[Vadim Smirnov]

Thanks, I have added a validation for these fields.

[Vadim Smirnov]

Have you tried to run any of the test binaries? For example, dnstrace?

[Vadim Smirnov]

Could you share the config file you are having trouble with? Another question, did you test adapter (-lac) or adapterless mode?

Regarding mysqld, do you mean that it initiates an outgoing connection? Because otherwise, i.e. mysqld listen for the incoming connections and needs to be reachable through the tunnel, binding to the address of the VPN adapter will probably suffice.

[Vadim Smirnov]

I use DisallowedIPs to exclude my LAN (192.168.1.0/24) for Chrome:

AllowedApps = chrome
DisallowedIPs = 192.168.1.0/24

[Vadim Smirnov]

Hi!

Have you installed Windows Packet Filter driver?

[Vadim Smirnov]

I will add a proxy option. This can be really useful.

Wiresock VPN Client is standalone, you don’t need the official Wireguard client to make it work.

WireSock VPN Gateway needs an official Wireguard client and allows it to act as a WireGuard server.

 

[Vadim Smirnov]

The problem was parsing a configuration that expected the Address parameter to have a specified netmask, e.g. Address = 10.10.0.4/32, 2001:dc8:a260::4/128 while in your configuration the Address parameter looked like Address = 10.10.0.4 , 2001:dc8:a260::4.

I have fixed the configuration parser in 1.2.8. Please give it a try.

[Vadim Smirnov]

Please check if you have received my reply email.

[Vadim Smirnov]

Problems with -lac options are caused by insufficient user privileges, please note that Wiresock should be run as administrator.

You can email PCAP files directly to [email protected]. We can continue to review the issue privately, after which I will post the final solution here. Unfortunately, without anti-spam, I would have to delete too many users/spam daily…

[Vadim Smirnov]

Hello, could you please provide the generated PCAP files in addition to the application log? Also, could you check if using-lac makes a difference? With the latter option, Wiresock works closer to the stock client. One more question, do you have DNS specified in the config file (‘server not found’ points to DNS problem)?

Currently, only the process name is checked, the path is ignored. It’s easy to change the check to a fully qualified pathname, but in the current implementation with a config file, this can lead to unwanted collisions. I plan to add an advanced configuration that will allow this.

You definitely read in my mind! I really was considering adding a proxy (as a dedicated process) that would be connected and intercepted by Wiresock. I implemented a similar thing for one side project.

[Vadim Smirnov]

I’m afraid something is wrong with your Dante server configuration. Unfortunately, it is difficult to guess and advise.

[Vadim Smirnov]

Check if you allowed configured UDP port range on Dante server machine, e.g. for 40000-45000 range it can be done by the command below:

iptables -I INPUT -p udp --dport 40000:45000 -j ACCEPT

[Vadim Smirnov]

According to the wiresock log, the authentication and UDP ASSOCIATE commands succeeded, but the handshake packet did not reach its destination. Most likely, it was blocked by the firewall (iptables or VPS provider). Please check this post for configuration details. They are specific to the Oracle cloud, but should be close to any other VPS.

[Vadim Smirnov]

Unfortunately, the SOCKS5 proxy provided by the SSH client does not support UDP and you cannot use it to forward the handshake. You need to set up a SOCKS5 UDP-enabled proxy (Dante) on the remote machine to use this option.

[Vadim Smirnov]

Hmm, the main question is when and how this client ID is assigned. If this is agreed before the start of the Wireguard session and already presented in the handshake packet, then this would require reverse engineering of the protocol used by Warp to authenticate and assign a client ID.

[Author]

Posts