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/circleci.go

@@ -0,0 +1,139 @@
+package sources
+
+import (
+	"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"
+)
+
+// CircleCISource scrapes CircleCI build logs for leaked API keys.
+// CircleCI exposes build logs via its API; a personal API token is required
+// to access build artifacts and logs. Misconfigured pipelines often leak
+// secrets in build output.
+type CircleCISource struct {
+	Token    string
+	BaseURL  string
+	Registry *providers.Registry
+	Limiters *recon.LimiterRegistry
+	Client   *Client
+}
+
+var _ recon.ReconSource = (*CircleCISource)(nil)
+
+func (s *CircleCISource) Name() string         { return "circleci" }
+func (s *CircleCISource) RateLimit() rate.Limit { return rate.Every(3 * time.Second) }
+func (s *CircleCISource) Burst() int            { return 2 }
+func (s *CircleCISource) RespectsRobots() bool  { return false }
+
+// Enabled requires a CircleCI API token.
+func (s *CircleCISource) Enabled(_ recon.Config) bool { return s.Token != "" }
+
+// circleciPipelineResponse represents the CircleCI v2 pipeline search result.
+type circleciPipelineResponse struct {
+	Items []circleciPipeline `json:"items"`
+}
+
+type circleciPipeline struct {
+	ID     string `json:"id"`
+	Number int    `json:"number"`
+}
+
+func (s *CircleCISource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
+	base := s.BaseURL
+	if base == "" {
+		base = "https://circleci.com/api/v2"
+	}
+	client := s.Client
+	if client == nil {
+		client = NewClient()
+	}
+
+	queries := BuildQueries(s.Registry, "circleci")
+	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 pipelines by project slug (query is used as slug hint).
+		searchURL := fmt.Sprintf("%s/project/gh/%s/pipeline?limit=5", base, q)
+		req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
+		if err != nil {
+			continue
+		}
+		req.Header.Set("Circle-Token", s.Token)
+		req.Header.Set("Accept", "application/json")
+
+		resp, err := client.Do(ctx, req)
+		if err != nil {
+			continue
+		}
+
+		var pipelines circleciPipelineResponse
+		if err := json.NewDecoder(resp.Body).Decode(&pipelines); err != nil {
+			_ = resp.Body.Close()
+			continue
+		}
+		_ = resp.Body.Close()
+
+		for _, p := range pipelines.Items {
+			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
+				}
+			}
+
+			// Fetch pipeline workflow logs.
+			logURL := fmt.Sprintf("%s/pipeline/%s/workflow", base, p.ID)
+			logReq, err := http.NewRequestWithContext(ctx, http.MethodGet, logURL, nil)
+			if err != nil {
+				continue
+			}
+			logReq.Header.Set("Circle-Token", s.Token)
+			logReq.Header.Set("Accept", "text/plain")
+
+			logResp, err := client.Do(ctx, logReq)
+			if err != nil {
+				continue
+			}
+
+			body, err := io.ReadAll(io.LimitReader(logResp.Body, 256*1024))
+			_ = logResp.Body.Close()
+			if err != nil {
+				continue
+			}
+
+			if ciLogKeyPattern.Match(body) {
+				out <- recon.Finding{
+					ProviderName: q,
+					Source:       logURL,
+					SourceType:   "recon:circleci",
+					Confidence:   "medium",
+					DetectedAt:   time.Now(),
+				}
+			}
+		}
+	}
+	return nil
+}