feat(14-04): implement 7 Phase 14 sources (CI/CD, archives, JS bundles)

- TravisCISource: scrapes public Travis CI build logs for API key leaks
- GitHubActionsSource: searches Actions workflow logs (requires GitHub token)
- CircleCISource: scrapes CircleCI pipeline logs (requires CircleCI token)
- JenkinsSource: scrapes public Jenkins console output for leaked secrets
- WaybackMachineSource: searches Wayback Machine CDX for archived key leaks
- CommonCrawlSource: searches Common Crawl index for exposed pages
- JSBundleSource: probes JS bundles for embedded API key literals

pkg/recon/sources/commoncrawl.go

@@ -0,0 +1,120 @@
+package sources
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"time"
+
+	"golang.org/x/time/rate"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+// CommonCrawlSource searches the Common Crawl index for web pages that may
+// contain leaked API keys. Common Crawl archives petabytes of web content;
+// its CDX API allows searching by URL pattern to find pages that historically
+// exposed secrets.
+type CommonCrawlSource struct {
+	BaseURL  string
+	Registry *providers.Registry
+	Limiters *recon.LimiterRegistry
+	Client   *Client
+}
+
+var _ recon.ReconSource = (*CommonCrawlSource)(nil)
+
+func (s *CommonCrawlSource) Name() string              { return "commoncrawl" }
+func (s *CommonCrawlSource) RateLimit() rate.Limit      { return rate.Every(5 * time.Second) }
+func (s *CommonCrawlSource) Burst() int                 { return 1 }
+func (s *CommonCrawlSource) RespectsRobots() bool       { return true }
+func (s *CommonCrawlSource) Enabled(_ recon.Config) bool { return true }
+
+// ccIndexResult represents a single Common Crawl CDX index record.
+type ccIndexResult struct {
+	URL       string `json:"url"`
+	Timestamp string `json:"timestamp"`
+	Status    string `json:"status"`
+	Filename  string `json:"filename"`
+	Length    string `json:"length"`
+	Offset    string `json:"offset"`
+}
+
+func (s *CommonCrawlSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
+	base := s.BaseURL
+	if base == "" {
+		base = "https://index.commoncrawl.org/CC-MAIN-2024-10-index"
+	}
+	client := s.Client
+	if client == nil {
+		client = NewClient()
+	}
+
+	queries := BuildQueries(s.Registry, "commoncrawl")
+	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
+			}
+		}
+
+		// CDX API: search for URLs matching the query.
+		searchURL := fmt.Sprintf("%s?url=*%s*&output=json&limit=10", base, 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, 128*1024))
+		_ = resp.Body.Close()
+		if err != nil {
+			continue
+		}
+
+		// Common Crawl returns NDJSON (newline-delimited JSON).
+		// Parse each line as a separate JSON object.
+		var results []ccIndexResult
+		dec := json.NewDecoder(bytes.NewReader(body))
+		for dec.More() {
+			var r ccIndexResult
+			if err := dec.Decode(&r); err != nil {
+				break
+			}
+			results = append(results, r)
+		}
+
+		for _, r := range results {
+			if err := ctx.Err(); err != nil {
+				return err
+			}
+
+			// Each indexed URL is a potential leak location; emit as finding.
+			out <- recon.Finding{
+				ProviderName: q,
+				Source:       r.URL,
+				SourceType:   "recon:commoncrawl",
+				Confidence:   "low",
+				DetectedAt:   time.Now(),
+			}
+		}
+	}
+	return nil
+}