feat(15-02): add Confluence and GoogleDocs ReconSource implementations

- ConfluenceSource searches exposed instances via /rest/api/content/search CQL
- GoogleDocsSource uses dorking + /export?format=txt for plain-text scanning
- HTML tag stripping for Confluence storage format
- Both credentialless, tests with httptest mocks confirm findings

pkg/recon/sources/confluence.go

@@ -0,0 +1,133 @@
+package sources
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"regexp"
+	"time"
+
+	"golang.org/x/time/rate"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+// ConfluenceSource searches publicly exposed Confluence wikis for leaked API
+// keys. Many Confluence instances are misconfigured to allow anonymous access
+// and their REST API exposes page content including credentials pasted into
+// documentation.
+type ConfluenceSource struct {
+	BaseURL  string
+	Registry *providers.Registry
+	Limiters *recon.LimiterRegistry
+	Client   *Client
+}
+
+var _ recon.ReconSource = (*ConfluenceSource)(nil)
+
+func (s *ConfluenceSource) Name() string               { return "confluence" }
+func (s *ConfluenceSource) RateLimit() rate.Limit       { return rate.Every(3 * time.Second) }
+func (s *ConfluenceSource) Burst() int                  { return 2 }
+func (s *ConfluenceSource) RespectsRobots() bool        { return true }
+func (s *ConfluenceSource) Enabled(_ recon.Config) bool { return true }
+
+// confluenceSearchResponse represents the Confluence REST API content search response.
+type confluenceSearchResponse struct {
+	Results []confluenceResult `json:"results"`
+}
+
+type confluenceResult struct {
+	ID    string          `json:"id"`
+	Title string          `json:"title"`
+	Body  confluenceBody  `json:"body"`
+	Links confluenceLinks `json:"_links"`
+}
+
+type confluenceBody struct {
+	Storage confluenceStorage `json:"storage"`
+}
+
+type confluenceStorage struct {
+	Value string `json:"value"`
+}
+
+type confluenceLinks struct {
+	WebUI string `json:"webui"`
+}
+
+// htmlTagPattern strips HTML tags to extract text content from Confluence storage format.
+var htmlTagPattern = regexp.MustCompile(`<[^>]*>`)
+
+func (s *ConfluenceSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
+	base := s.BaseURL
+	if base == "" {
+		base = "https://confluence.example.com"
+	}
+	client := s.Client
+	if client == nil {
+		client = NewClient()
+	}
+
+	queries := BuildQueries(s.Registry, "confluence")
+	if len(queries) == 0 {
+		return nil
+	}
+
+	for _, q := range queries {
+		if err := ctx.Err(); err != nil {
+			return err
+		}
+
+		if s.Limiters != nil {
+			if err := s.Limiters.Wait(ctx, s.Name(), s.RateLimit(), s.Burst(), false); err != nil {
+				return err
+			}
+		}
+
+		// Search Confluence via CQL (Confluence Query Language).
+		searchURL := fmt.Sprintf("%s/rest/api/content/search?cql=%s&limit=10&expand=body.storage",
+			base, url.QueryEscape(fmt.Sprintf(`text~"%s"`, q)))
+		req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
+		if err != nil {
+			continue
+		}
+		req.Header.Set("Accept", "application/json")
+
+		resp, err := client.Do(ctx, req)
+		if err != nil {
+			continue
+		}
+
+		body, err := io.ReadAll(io.LimitReader(resp.Body, 256*1024))
+		_ = resp.Body.Close()
+		if err != nil {
+			continue
+		}
+
+		var result confluenceSearchResponse
+		if err := json.Unmarshal(body, &result); err != nil {
+			continue
+		}
+
+		for _, page := range result.Results {
+			// Strip HTML tags to get plain text for key matching.
+			plainText := htmlTagPattern.ReplaceAllString(page.Body.Storage.Value, " ")
+
+			if ciLogKeyPattern.MatchString(plainText) {
+				pageURL := fmt.Sprintf("%s%s", base, page.Links.WebUI)
+				out <- recon.Finding{
+					ProviderName: q,
+					Source:       pageURL,
+					SourceType:   "recon:confluence",
+					Confidence:   "medium",
+					DetectedAt:   time.Now(),
+				}
+			}
+		}
+	}
+	return nil
+}

pkg/recon/sources/confluence_test.go

@@ -0,0 +1,77 @@
+package sources
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+func TestConfluence_Name(t *testing.T) {
+	s := &ConfluenceSource{}
+	if s.Name() != "confluence" {
+		t.Fatalf("expected confluence, got %s", s.Name())
+	}
+}
+
+func TestConfluence_Enabled(t *testing.T) {
+	s := &ConfluenceSource{}
+	if !s.Enabled(recon.Config{}) {
+		t.Fatal("ConfluenceSource should always be enabled (credentialless)")
+	}
+}
+
+func TestConfluence_Sweep(t *testing.T) {
+	mux := http.NewServeMux()
+	mux.HandleFunc("/rest/api/content/search", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"results":[{
+			"id":"12345",
+			"title":"API Configuration",
+			"body":{"storage":{"value":"<p>Production credentials: <code>secret_key = sk-proj-ABCDEF1234567890abcdef</code></p>"}},
+			"_links":{"webui":"/display/TEAM/API+Configuration"}
+		}]}`))
+	})
+
+	srv := httptest.NewServer(mux)
+	defer srv.Close()
+
+	reg := providers.NewRegistryFromProviders([]providers.Provider{
+		{Name: "openai", Keywords: []string{"sk-proj-"}},
+	})
+
+	s := &ConfluenceSource{
+		BaseURL:  srv.URL,
+		Registry: reg,
+		Client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 10)
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	err := s.Sweep(ctx, "", out)
+	close(out)
+	if err != nil {
+		t.Fatalf("Sweep error: %v", err)
+	}
+
+	var findings []recon.Finding
+	for f := range out {
+		findings = append(findings, f)
+	}
+	if len(findings) == 0 {
+		t.Fatal("expected at least one finding from Confluence page")
+	}
+	if findings[0].SourceType != "recon:confluence" {
+		t.Fatalf("expected recon:confluence, got %s", findings[0].SourceType)
+	}
+	expected := srv.URL + "/display/TEAM/API+Configuration"
+	if findings[0].Source != expected {
+		t.Fatalf("expected %s, got %s", expected, findings[0].Source)
+	}
+}

pkg/recon/sources/googledocs.go

@@ -0,0 +1,139 @@
+package sources
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"net/url"
+	"time"
+
+	"golang.org/x/time/rate"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+// GoogleDocsSource searches publicly shared Google Docs for leaked API keys.
+// Google Docs shared with "anyone with the link" are indexable by search
+// engines. This source uses a dorking approach to discover public docs and
+// then fetches their plain-text export for credential scanning.
+type GoogleDocsSource struct {
+	BaseURL  string
+	Registry *providers.Registry
+	Limiters *recon.LimiterRegistry
+	Client   *Client
+}
+
+var _ recon.ReconSource = (*GoogleDocsSource)(nil)
+
+func (s *GoogleDocsSource) Name() string               { return "googledocs" }
+func (s *GoogleDocsSource) RateLimit() rate.Limit       { return rate.Every(3 * time.Second) }
+func (s *GoogleDocsSource) Burst() int                  { return 2 }
+func (s *GoogleDocsSource) RespectsRobots() bool        { return true }
+func (s *GoogleDocsSource) Enabled(_ recon.Config) bool { return true }
+
+// googleDocsSearchResponse represents dork search results for Google Docs.
+type googleDocsSearchResponse struct {
+	Results []googleDocsSearchResult `json:"results"`
+}
+
+type googleDocsSearchResult struct {
+	URL   string `json:"url"`
+	Title string `json:"title"`
+}
+
+func (s *GoogleDocsSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
+	base := s.BaseURL
+	if base == "" {
+		base = "https://search.googledocs.dev"
+	}
+	client := s.Client
+	if client == nil {
+		client = NewClient()
+	}
+
+	queries := BuildQueries(s.Registry, "googledocs")
+	if len(queries) == 0 {
+		return nil
+	}
+
+	for _, q := range queries {
+		if err := ctx.Err(); err != nil {
+			return err
+		}
+
+		if s.Limiters != nil {
+			if err := s.Limiters.Wait(ctx, s.Name(), s.RateLimit(), s.Burst(), false); err != nil {
+				return err
+			}
+		}
+
+		// Search for public Google Docs via dorking.
+		searchURL := fmt.Sprintf("%s/search?q=%s&format=json",
+			base, url.QueryEscape("site:docs.google.com "+q))
+		req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
+		if err != nil {
+			continue
+		}
+		req.Header.Set("Accept", "application/json")
+
+		resp, err := client.Do(ctx, req)
+		if err != nil {
+			continue
+		}
+
+		body, err := io.ReadAll(io.LimitReader(resp.Body, 256*1024))
+		_ = resp.Body.Close()
+		if err != nil {
+			continue
+		}
+
+		var results googleDocsSearchResponse
+		if err := json.Unmarshal(body, &results); err != nil {
+			continue
+		}
+
+		// Fetch each discovered doc's plain-text export.
+		for _, result := range results.Results {
+			if err := ctx.Err(); err != nil {
+				return err
+			}
+
+			if s.Limiters != nil {
+				if err := s.Limiters.Wait(ctx, s.Name(), s.RateLimit(), s.Burst(), false); err != nil {
+					return err
+				}
+			}
+
+			exportURL := result.URL + "/export?format=txt"
+			docReq, err := http.NewRequestWithContext(ctx, http.MethodGet, exportURL, nil)
+			if err != nil {
+				continue
+			}
+
+			docResp, err := client.Do(ctx, docReq)
+			if err != nil {
+				continue
+			}
+
+			docBody, err := io.ReadAll(io.LimitReader(docResp.Body, 256*1024))
+			_ = docResp.Body.Close()
+			if err != nil {
+				continue
+			}
+
+			if ciLogKeyPattern.Match(docBody) {
+				out <- recon.Finding{
+					ProviderName: q,
+					Source:       result.URL,
+					SourceType:   "recon:googledocs",
+					Confidence:   "medium",
+					DetectedAt:   time.Now(),
+				}
+			}
+		}
+	}
+	return nil
+}

pkg/recon/sources/googledocs_test.go

@@ -0,0 +1,79 @@
+package sources
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+func TestGoogleDocs_Name(t *testing.T) {
+	s := &GoogleDocsSource{}
+	if s.Name() != "googledocs" {
+		t.Fatalf("expected googledocs, got %s", s.Name())
+	}
+}
+
+func TestGoogleDocs_Enabled(t *testing.T) {
+	s := &GoogleDocsSource{}
+	if !s.Enabled(recon.Config{}) {
+		t.Fatal("GoogleDocsSource should always be enabled (credentialless)")
+	}
+}
+
+func TestGoogleDocs_Sweep(t *testing.T) {
+	mux := http.NewServeMux()
+
+	// Mock search endpoint returning a doc URL.
+	mux.HandleFunc("/search", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"results":[{"url":"` + "http://" + r.Host + `/doc/d/1a2b3c","title":"Setup Guide"}]}`))
+	})
+
+	// Mock plain-text export with a leaked key.
+	mux.HandleFunc("/doc/d/1a2b3c/export", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "text/plain")
+		_, _ = w.Write([]byte(`Setup Instructions
+Step 1: Set your API key
+auth_token = sk-proj-ABCDEF1234567890abcdef
+Step 2: Run the service`))
+	})
+
+	srv := httptest.NewServer(mux)
+	defer srv.Close()
+
+	reg := providers.NewRegistryFromProviders([]providers.Provider{
+		{Name: "openai", Keywords: []string{"sk-proj-"}},
+	})
+
+	s := &GoogleDocsSource{
+		BaseURL:  srv.URL,
+		Registry: reg,
+		Client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 10)
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	err := s.Sweep(ctx, "", out)
+	close(out)
+	if err != nil {
+		t.Fatalf("Sweep error: %v", err)
+	}
+
+	var findings []recon.Finding
+	for f := range out {
+		findings = append(findings, f)
+	}
+	if len(findings) == 0 {
+		t.Fatal("expected at least one finding from Google Docs export")
+	}
+	if findings[0].SourceType != "recon:googledocs" {
+		t.Fatalf("expected recon:googledocs, got %s", findings[0].SourceType)
+	}
+}