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
+}