018bb165fe
- 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
105 lines
2.7 KiB
Go
105 lines
2.7 KiB
Go
package sources
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"net/http"
|
|
"net/url"
|
|
"regexp"
|
|
"time"
|
|
|
|
"golang.org/x/time/rate"
|
|
|
|
"github.com/salvacybersec/keyhunter/pkg/providers"
|
|
"github.com/salvacybersec/keyhunter/pkg/recon"
|
|
)
|
|
|
|
// GoProxySource searches pkg.go.dev for Go modules matching provider keywords.
|
|
// pkg.go.dev returns HTML search results, so we parse anchor hrefs for module
|
|
// paths. No authentication required.
|
|
type GoProxySource struct {
|
|
BaseURL string
|
|
Registry *providers.Registry
|
|
Limiters *recon.LimiterRegistry
|
|
Client *Client
|
|
}
|
|
|
|
// goProxyLinkRE matches Go module paths which always contain a domain with a
|
|
// dot (e.g. /github.com/user/repo). This filters out simple paths like /about.
|
|
var goProxyLinkRE = regexp.MustCompile(`^/[a-z][a-z0-9_-]*\.[a-z0-9./_-]+$`)
|
|
|
|
// Compile-time assertion that GoProxySource satisfies recon.ReconSource.
|
|
var _ recon.ReconSource = (*GoProxySource)(nil)
|
|
|
|
func (s *GoProxySource) Name() string { return "goproxy" }
|
|
func (s *GoProxySource) RateLimit() rate.Limit { return rate.Every(2 * time.Second) }
|
|
func (s *GoProxySource) Burst() int { return 2 }
|
|
func (s *GoProxySource) RespectsRobots() bool { return false }
|
|
|
|
// Enabled always returns true: pkg.go.dev requires no credentials.
|
|
func (s *GoProxySource) Enabled(_ recon.Config) bool { return true }
|
|
|
|
// Sweep queries pkg.go.dev search for each provider keyword, parses the HTML
|
|
// response for module path links, and emits a Finding per result.
|
|
func (s *GoProxySource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
|
|
base := s.BaseURL
|
|
if base == "" {
|
|
base = "https://pkg.go.dev"
|
|
}
|
|
client := s.Client
|
|
if client == nil {
|
|
client = NewClient()
|
|
}
|
|
|
|
queries := BuildQueries(s.Registry, "goproxy")
|
|
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?q=%s&m=package", base, url.QueryEscape(q))
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
|
|
if err != nil {
|
|
return fmt.Errorf("goproxy: build request: %w", err)
|
|
}
|
|
|
|
resp, err := client.Do(ctx, req)
|
|
if err != nil {
|
|
continue
|
|
}
|
|
|
|
links, parseErr := extractAnchorHrefs(resp.Body, goProxyLinkRE)
|
|
_ = resp.Body.Close()
|
|
if parseErr != nil {
|
|
continue
|
|
}
|
|
|
|
for _, href := range links {
|
|
if err := ctx.Err(); err != nil {
|
|
return err
|
|
}
|
|
absURL := base + href
|
|
select {
|
|
case out <- recon.Finding{
|
|
Source: absURL,
|
|
SourceType: "recon:goproxy",
|
|
Confidence: "low",
|
|
DetectedAt: time.Now(),
|
|
}:
|
|
case <-ctx.Done():
|
|
return ctx.Err()
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|