- GoProxySource parses pkg.go.dev HTML search results for module paths - PackagistSource queries Packagist JSON search API for PHP packages - GoProxy regex requires domain dot to filter non-module paths
112 lines
2.7 KiB
Go
112 lines
2.7 KiB
Go
package sources
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"net/url"
|
|
"time"
|
|
|
|
"golang.org/x/time/rate"
|
|
|
|
"github.com/salvacybersec/keyhunter/pkg/providers"
|
|
"github.com/salvacybersec/keyhunter/pkg/recon"
|
|
)
|
|
|
|
// PackagistSource searches Packagist (the PHP package registry) for packages
|
|
// matching provider keywords. The Packagist search API is public JSON and
|
|
// requires no authentication.
|
|
type PackagistSource struct {
|
|
BaseURL string
|
|
Registry *providers.Registry
|
|
Limiters *recon.LimiterRegistry
|
|
Client *Client
|
|
}
|
|
|
|
// Compile-time assertion that PackagistSource satisfies recon.ReconSource.
|
|
var _ recon.ReconSource = (*PackagistSource)(nil)
|
|
|
|
func (s *PackagistSource) Name() string { return "packagist" }
|
|
func (s *PackagistSource) RateLimit() rate.Limit { return rate.Every(2 * time.Second) }
|
|
func (s *PackagistSource) Burst() int { return 2 }
|
|
func (s *PackagistSource) RespectsRobots() bool { return false }
|
|
|
|
// Enabled always returns true: Packagist search requires no credentials.
|
|
func (s *PackagistSource) Enabled(_ recon.Config) bool { return true }
|
|
|
|
// Sweep queries Packagist's search API for each provider keyword and emits a
|
|
// Finding per matching package.
|
|
func (s *PackagistSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
|
|
base := s.BaseURL
|
|
if base == "" {
|
|
base = "https://packagist.org"
|
|
}
|
|
client := s.Client
|
|
if client == nil {
|
|
client = NewClient()
|
|
}
|
|
|
|
queries := BuildQueries(s.Registry, "packagist")
|
|
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
|
|
}
|
|
}
|
|
|
|
endpoint := fmt.Sprintf("%s/search.json?q=%s&per_page=20",
|
|
base, url.QueryEscape(q))
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
|
|
if err != nil {
|
|
return fmt.Errorf("packagist: build request: %w", err)
|
|
}
|
|
req.Header.Set("Accept", "application/json")
|
|
|
|
resp, err := client.Do(ctx, req)
|
|
if err != nil {
|
|
continue
|
|
}
|
|
|
|
var parsed packagistSearchResponse
|
|
decErr := json.NewDecoder(resp.Body).Decode(&parsed)
|
|
_ = resp.Body.Close()
|
|
if decErr != nil {
|
|
continue
|
|
}
|
|
|
|
for _, pkg := range parsed.Results {
|
|
if err := ctx.Err(); err != nil {
|
|
return err
|
|
}
|
|
select {
|
|
case out <- recon.Finding{
|
|
Source: pkg.URL,
|
|
SourceType: "recon:packagist",
|
|
Confidence: "low",
|
|
DetectedAt: time.Now(),
|
|
}:
|
|
case <-ctx.Done():
|
|
return ctx.Err()
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
type packagistSearchResponse struct {
|
|
Results []packagistPackage `json:"results"`
|
|
}
|
|
|
|
type packagistPackage struct {
|
|
Name string `json:"name"`
|
|
URL string `json:"url"`
|
|
}
|