keyhunter/pkg/recon/sources/githubactions.go

package sources

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

	"golang.org/x/time/rate"

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

// GitHubActionsSource searches GitHub Actions workflow run logs for leaked API
// keys. It queries the GitHub REST API for workflow runs matching provider
// keywords (via the repository search endpoint) and emits findings for each
// matching run. Requires a GitHub token (same as GitHubSource).
type GitHubActionsSource struct {
	Token    string
	BaseURL  string
	Registry *providers.Registry
	Limiters *recon.LimiterRegistry
	client   *Client
}

var _ recon.ReconSource = (*GitHubActionsSource)(nil)

func (s *GitHubActionsSource) Name() string          { return "github_actions" }
func (s *GitHubActionsSource) RateLimit() rate.Limit { return rate.Every(2 * time.Second) }
func (s *GitHubActionsSource) Burst() int            { return 2 }
func (s *GitHubActionsSource) RespectsRobots() bool  { return false }
func (s *GitHubActionsSource) Enabled(_ recon.Config) bool { return s.Token != "" }

// ghActionsSearchResponse models the GitHub code search response when looking
// for workflow files containing provider keywords.
type ghActionsSearchResponse struct {
	Items []ghActionsItem `json:"items"`
}

type ghActionsItem struct {
	HTMLURL    string              `json:"html_url"`
	Repository ghActionsRepository `json:"repository"`
}

type ghActionsRepository struct {
	FullName string `json:"full_name"`
}

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

	queries := BuildQueries(s.Registry, "github_actions")
	kwIndex := ghActionsKeywordIndex(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
			}
		}

		// Search for workflow YAML files referencing the keyword.
		endpoint := fmt.Sprintf("%s/search/code?q=%s+path:.github/workflows+extension:yml&per_page=20",
			base, url.QueryEscape(q))
		req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
		if err != nil {
			return fmt.Errorf("github_actions: build request: %w", err)
		}
		req.Header.Set("Authorization", "Bearer "+s.Token)
		req.Header.Set("Accept", "application/vnd.github+json")

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

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

		provName := kwIndex[strings.ToLower(q)]
		for _, item := range result.Items {
			f := recon.Finding{
				ProviderName: provName,
				Confidence:   "low",
				Source:       item.HTMLURL,
				SourceType:   "recon:github_actions",
				DetectedAt:   time.Now(),
			}
			select {
			case out <- f:
			case <-ctx.Done():
				return ctx.Err()
			}
		}
	}
	return nil
}

func ghActionsKeywordIndex(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
}