keyhunter/pkg/recon/sources/register.go

package sources

import (
	"github.com/salvacybersec/keyhunter/pkg/providers"
	"github.com/salvacybersec/keyhunter/pkg/recon"
)

// SourcesConfig carries per-source credentials and shared dependencies read
// from viper/env by cmd/recon.go and handed to RegisterAll.
//
// Fields are populated from environment variables (GITHUB_TOKEN, GITLAB_TOKEN,
// ...) or viper config keys (recon.github.token, ...). Empty values are
// permitted: the corresponding source is still registered on the engine, but
// its Enabled() reports false so SweepAll skips it cleanly.
type SourcesConfig struct {
	// GitHub / Gist share the same token.
	GitHubToken string
	// GitLab personal access token.
	GitLabToken string
	// Bitbucket Cloud app password or OAuth token + required workspace slug.
	BitbucketToken     string
	BitbucketWorkspace string
	// Codeberg (Gitea) token — optional, raises rate limit when present.
	CodebergToken string
	// HuggingFace Hub token — optional, raises rate limit when present.
	HuggingFaceToken string
	// Kaggle Basic-auth username + API key.
	KaggleUser string
	KaggleKey  string

	// Google Custom Search API key and search engine ID (CX).
	GoogleAPIKey string
	GoogleCX     string
	// Bing Web Search API subscription key.
	BingAPIKey string
	// Yandex XML Search user and API key.
	YandexUser   string
	YandexAPIKey string
	// Brave Search API subscription token.
	BraveAPIKey string

	// Phase 12: IoT scanner API keys.
	ShodanAPIKey     string
	CensysAPIId      string
	CensysAPISecret  string
	ZoomEyeAPIKey    string
	FOFAEmail        string
	FOFAAPIKey       string
	NetlasAPIKey     string
	BinaryEdgeAPIKey string

	// Registry drives query generation for every source via BuildQueries.
	Registry *providers.Registry
	// Limiters is the shared per-source rate-limiter registry.
	Limiters *recon.LimiterRegistry
}

// RegisterAll registers every Phase 10 code-hosting, Phase 11 search engine /
// paste site, and Phase 12 IoT scanner / cloud storage source on engine
// (28 sources total).
//
// All sources are registered unconditionally so that cmd/recon.go can surface
// the full catalog via `keyhunter recon list` regardless of which credentials
// are configured. Sources without required credentials return Enabled()==false
// so SweepAll skips them without erroring.
//
// A nil engine is treated as a no-op (not an error) -- callers in broken init
// paths shouldn't panic.
func RegisterAll(engine *recon.Engine, cfg SourcesConfig) {
	if engine == nil {
		return
	}
	reg := cfg.Registry
	lim := cfg.Limiters

	// API sources with constructors.
	engine.Register(NewGitHubSource(cfg.GitHubToken, reg, lim))
	engine.Register(NewKaggleSource(cfg.KaggleUser, cfg.KaggleKey, reg, lim))
	engine.Register(NewHuggingFaceSource(HuggingFaceConfig{
		Token:    cfg.HuggingFaceToken,
		Registry: reg,
		Limiters: lim,
	}))

	// API sources exposed as struct literals (no New* constructor in Wave 2).
	engine.Register(&GitLabSource{
		Token:    cfg.GitLabToken,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&BitbucketSource{
		Token:     cfg.BitbucketToken,
		Workspace: cfg.BitbucketWorkspace,
		Registry:  reg,
		Limiters:  lim,
	})
	engine.Register(&GistSource{
		Token:    cfg.GitHubToken,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&CodebergSource{
		Token:    cfg.CodebergToken,
		Registry: reg,
		Limiters: lim,
	})

	// Scraping sources (credentialless).
	engine.Register(&ReplitSource{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&CodeSandboxSource{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&SandboxesSource{
		Registry: reg,
		Limiters: lim,
	})

	// Phase 11: Search engine dorking sources.
	engine.Register(&GoogleDorkSource{
		APIKey:   cfg.GoogleAPIKey,
		CX:       cfg.GoogleCX,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&BingDorkSource{
		APIKey:   cfg.BingAPIKey,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&DuckDuckGoSource{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&YandexSource{
		User:     cfg.YandexUser,
		APIKey:   cfg.YandexAPIKey,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&BraveSource{
		APIKey:   cfg.BraveAPIKey,
		Registry: reg,
		Limiters: lim,
	})

	// Phase 11: Paste site sources.
	engine.Register(&PastebinSource{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&GistPasteSource{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&PasteSitesSource{
		Registry: reg,
		Limiters: lim,
	})

	// Phase 12: IoT scanner sources.
	engine.Register(&ShodanSource{
		APIKey:   cfg.ShodanAPIKey,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&CensysSource{
		APIId:     cfg.CensysAPIId,
		APISecret: cfg.CensysAPISecret,
		Registry:  reg,
		Limiters:  lim,
	})
	engine.Register(&ZoomEyeSource{
		APIKey:   cfg.ZoomEyeAPIKey,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&FOFASource{
		Email:    cfg.FOFAEmail,
		APIKey:   cfg.FOFAAPIKey,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&NetlasSource{
		APIKey:   cfg.NetlasAPIKey,
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&BinaryEdgeSource{
		APIKey:   cfg.BinaryEdgeAPIKey,
		Registry: reg,
		Limiters: lim,
	})

	// Phase 12: Cloud storage sources (credentialless).
	engine.Register(&S3Scanner{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&GCSScanner{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&AzureBlobScanner{
		Registry: reg,
		Limiters: lim,
	})
	engine.Register(&DOSpacesScanner{
		Registry: reg,
		Limiters: lim,
	})
}