If it's true it's a nice DoS vector
fwiw this is currently being discussed on the sks mailing list, but the overwhelming opinon seems to be that the current behaviour should stay. https://lists.nongnu.org/archive/html/sks-devel/2015-05/msg0...
It's up to the clients to do their own verification, which in this case GPG does perfectly (it doesn't import the invalid subkey since the self-signature is invalid).