From d8c4d9fc5a62741f0c4c2b692a3a94874714bbcc Mon Sep 17 00:00:00 2001 From: kim Date: Mon, 28 Apr 2025 20:12:27 +0000 Subject: [feature] proof of work scraper deterrence (#4043) This adds a proof-of-work based scraper deterrence to GoToSocial's middleware stack on profile and status web pages. Heavily inspired by https://github.com/TecharoHQ/anubis, but massively stripped back for our own usecase. Todo: - ~~add configuration option so this is disabled by default~~ - ~~fix whatever weirdness is preventing this working with CSP (even in debug)~~ - ~~use our standard templating mechanism going through apiutil helper func~~ - ~~probably some absurdly small performance improvements to be made in pooling re-used hex encode / hash encode buffers~~ the web endpoints aren't as hot a path as API / ActivityPub, will leave as-is for now as it is already very minimal and well optimized - ~~verify the cryptographic assumptions re: using a portion of token as challenge data~~ this isn't a serious application of cryptography, if it turns out to be a problem we'll fix it, but it definitely should not be easily possible to guess a SHA256 hash from the first 1/4 of it even if mathematically it might make it a bit easier - ~~theme / make look nice??~~ - ~~add a spinner~~ - ~~add entry in example configuration~~ - ~~add documentation~~ Verification page originally based on https://github.com/LucienV1/powtect Co-authored-by: tobi Reviewed-on: https://codeberg.org/superseriousbusiness/gotosocial/pulls/4043 Reviewed-by: tobi Co-authored-by: kim Co-committed-by: kim --- internal/web/web.go | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'internal/web/web.go') diff --git a/internal/web/web.go b/internal/web/web.go index ab440ab2f..e42dc16c3 100644 --- a/internal/web/web.go +++ b/internal/web/web.go @@ -99,12 +99,16 @@ func (m *Module) Route(r *router.Router, mi ...gin.HandlerFunc) { // Handlers that serve profiles and statuses should use // the SignatureCheck middleware, so that requests with - // content-type application/activity+json can be served + // content-type application/activity+json can be served, + // and (if enabled) the nollamas middleware, to protect + // against scraping by shitty LLM bullshit. profileGroup := r.AttachGroup(profileGroupPath) profileGroup.Use(mi...) profileGroup.Use(middleware.SignatureCheck(m.isURIBlocked), middleware.CacheControl(middleware.CacheControlConfig{ Directives: []string{"no-store"}, })) + nollamas := middleware.NoLLaMas(m.processor.InstanceGetV1) + profileGroup.Use(nollamas) profileGroup.Handle(http.MethodGet, "", m.profileGETHandler) // use empty path here since it's the base of the group profileGroup.Handle(http.MethodGet, statusPath, m.threadGETHandler) -- cgit v1.2.3