feat(11-02): add PastebinSource and GistPasteSource for paste site scanning

- PastebinSource: two-phase search+raw-fetch with keyword matching - GistPasteSource: scrapes gist.github.com public search (no auth) - Both implement recon.ReconSource with httptest-based tests
2026-04-06 11:53:00 +03:00
parent 3aadeb2d1c
commit 3c500b5473
4 changed files with 547 additions and 0 deletions
--- a/pkg/recon/sources/gistpaste_test.go
+++ b/pkg/recon/sources/gistpaste_test.go
@@ -0,0 +1,119 @@
+package sources
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+func gistPasteTestRegistry() *providers.Registry {
+	return providers.NewRegistryFromProviders([]providers.Provider{
+		{Name: "anthropic", Keywords: []string{"sk-ant-"}},
+	})
+}
+
+const gistPasteSearchHTML = `<!doctype html>
+<html><body>
+  <a href="/alice/abc123def456">gist one</a>
+  <a href="/bob/789aaa000bbb">gist two</a>
+  <a href="/about">nope</a>
+  <a href="/trending">nope</a>
+</body></html>`
+
+const gistPasteRaw1 = `config with sk-ant-XYZKEY123 inside`
+const gistPasteRaw2 = `nothing here`
+
+func TestGistPaste_Sweep_ExtractsFindings(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		switch {
+		case r.URL.Path == "/search":
+			w.Header().Set("Content-Type", "text/html")
+			_, _ = w.Write([]byte(gistPasteSearchHTML))
+		case r.URL.Path == "/alice/abc123def456/raw":
+			_, _ = w.Write([]byte(gistPasteRaw1))
+		case r.URL.Path == "/bob/789aaa000bbb/raw":
+			_, _ = w.Write([]byte(gistPasteRaw2))
+		default:
+			http.NotFound(w, r)
+		}
+	}))
+	defer srv.Close()
+
+	src := &GistPasteSource{
+		BaseURL:  srv.URL,
+		Registry: gistPasteTestRegistry(),
+		Limiters: recon.NewLimiterRegistry(),
+		Client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 16)
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	if err := src.Sweep(ctx, "", out); err != nil {
+		t.Fatalf("Sweep err: %v", err)
+	}
+	close(out)
+
+	var findings []recon.Finding
+	for f := range out {
+		findings = append(findings, f)
+	}
+	if len(findings) != 1 {
+		t.Fatalf("expected 1 finding, got %d", len(findings))
+	}
+	f := findings[0]
+	if f.SourceType != "recon:gistpaste" {
+		t.Errorf("SourceType=%s, want recon:gistpaste", f.SourceType)
+	}
+	if f.ProviderName != "anthropic" {
+		t.Errorf("ProviderName=%s, want anthropic", f.ProviderName)
+	}
+	wantSource := srv.URL + "/alice/abc123def456"
+	if f.Source != wantSource {
+		t.Errorf("Source=%s, want %s", f.Source, wantSource)
+	}
+}
+
+func TestGistPaste_NameAndRate(t *testing.T) {
+	s := &GistPasteSource{}
+	if s.Name() != "gistpaste" {
+		t.Errorf("Name=%s", s.Name())
+	}
+	if s.Burst() != 1 {
+		t.Errorf("Burst=%d", s.Burst())
+	}
+	if !s.RespectsRobots() {
+		t.Error("expected RespectsRobots=true")
+	}
+	if !s.Enabled(recon.Config{}) {
+		t.Error("expected Enabled=true")
+	}
+}
+
+func TestGistPaste_Sweep_CtxCancelled(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		time.Sleep(500 * time.Millisecond)
+		_, _ = w.Write([]byte(gistPasteSearchHTML))
+	}))
+	defer srv.Close()
+
+	src := &GistPasteSource{
+		BaseURL:  srv.URL,
+		Registry: gistPasteTestRegistry(),
+		Limiters: recon.NewLimiterRegistry(),
+		Client:   NewClient(),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	out := make(chan recon.Finding, 4)
+	if err := src.Sweep(ctx, "", out); err == nil {
+		t.Fatal("expected ctx error")
+	}
+}