keyhunter/pkg/recon/sources/circleci.go

package sources

import (
	"context"
	"encoding/json"
	"fmt"
	"net/http"
	"strings"
	"time"

	"golang.org/x/time/rate"

	"github.com/salvacybersec/keyhunter/pkg/providers"
	"github.com/salvacybersec/keyhunter/pkg/recon"
)

// CircleCISource searches public CircleCI build logs for leaked API keys.
// It queries the CircleCI v2 API for recent pipeline workflows. Requires a
// CircleCI API token for authenticated access.
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(2 * time.Second) }
func (s *CircleCISource) Burst() int               { return 2 }
func (s *CircleCISource) RespectsRobots() bool     { return false }
func (s *CircleCISource) Enabled(_ recon.Config) bool { return s.Token != "" }

type circlePipelineResponse struct {
	Items []circlePipeline `json:"items"`
}

type circlePipeline struct {
	ID  string          `json:"id"`
	VCS circleVCSInfo   `json:"vcs"`
}

type circleVCSInfo struct {
	ProviderName string `json:"provider_name"`
	RepoName     string `json:"target_repository_url"`
}

func (s *CircleCISource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
	if s.Token == "" {
		return nil
	}
	base := s.BaseURL
	if base == "" {
		base = "https://circleci.com/api/v2"
	}
	client := s.Client
	if client == nil {
		client = NewClient()
	}

	queries := BuildQueries(s.Registry, "circleci")
	kwIndex := circleKeywordIndex(s.Registry)

	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
			}
		}

		endpoint := fmt.Sprintf("%s/pipeline?mine=false", base)
		req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
		if err != nil {
			return fmt.Errorf("circleci: build request: %w", err)
		}
		req.Header.Set("Circle-Token", s.Token)
		req.Header.Set("Accept", "application/json")

		resp, err := client.Do(ctx, req)
		if err != nil {
			if strings.Contains(err.Error(), "unauthorized") {
				return err
			}
			continue
		}

		var result circlePipelineResponse
		decErr := json.NewDecoder(resp.Body).Decode(&result)
		_ = resp.Body.Close()
		if decErr != nil {
			continue
		}

		provName := kwIndex[strings.ToLower(q)]
		for _, p := range result.Items {
			source := fmt.Sprintf("https://app.circleci.com/pipelines/%s", p.ID)
			if p.VCS.RepoName != "" {
				source = p.VCS.RepoName
			}
			f := recon.Finding{
				ProviderName: provName,
				Confidence:   "low",
				Source:       source,
				SourceType:   "recon:circleci",
				DetectedAt:   time.Now(),
			}
			select {
			case out <- f:
			case <-ctx.Done():
				return ctx.Err()
			}
		}
	}
	return nil
}

func circleKeywordIndex(reg *providers.Registry) map[string]string {
	m := make(map[string]string)
	if reg == nil {
		return m
	}
	for _, p := range reg.List() {
		for _, k := range p.Keywords {
			kl := strings.ToLower(strings.TrimSpace(k))
			if kl != "" {
				if _, exists := m[kl]; !exists {
					m[kl] = p.Name
				}
			}
		}
	}
	return m
}