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
125 lines
3.1 KiB
Go
125 lines
3.1 KiB
Go
package sources
|
|
|
|
import (
|
|
"context"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/salvacybersec/keyhunter/pkg/providers"
|
|
"github.com/salvacybersec/keyhunter/pkg/recon"
|
|
)
|
|
|
|
func goProxyTestRegistry() *providers.Registry {
|
|
return providers.NewRegistryFromProviders([]providers.Provider{
|
|
{Name: "openai", Keywords: []string{"sk-proj-"}},
|
|
})
|
|
}
|
|
|
|
const goProxyFixtureHTML = `<!doctype html>
|
|
<html><body>
|
|
<a href="/github.com/example/openai-go">openai-go</a>
|
|
<a href="/github.com/test/llm-client">llm-client</a>
|
|
<a href="/about">about page</a>
|
|
<a href="https://external.example.com">external</a>
|
|
<a href="/search?q=next">pagination</a>
|
|
</body></html>`
|
|
|
|
func newGoProxyTestSource(srvURL string) *GoProxySource {
|
|
return &GoProxySource{
|
|
BaseURL: srvURL,
|
|
Registry: goProxyTestRegistry(),
|
|
Limiters: recon.NewLimiterRegistry(),
|
|
Client: NewClient(),
|
|
}
|
|
}
|
|
|
|
func TestGoProxy_Sweep_ExtractsFindings(t *testing.T) {
|
|
var hits int
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
if r.URL.Path != "/search" {
|
|
t.Errorf("unexpected path: %s", r.URL.Path)
|
|
}
|
|
if r.URL.Query().Get("q") == "" {
|
|
t.Errorf("missing q param")
|
|
}
|
|
hits++
|
|
w.Header().Set("Content-Type", "text/html")
|
|
_, _ = w.Write([]byte(goProxyFixtureHTML))
|
|
}))
|
|
defer srv.Close()
|
|
|
|
src := newGoProxyTestSource(srv.URL)
|
|
out := make(chan recon.Finding, 16)
|
|
ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
|
|
defer cancel()
|
|
|
|
if err := src.Sweep(ctx, "", out); err != nil {
|
|
t.Fatalf("Sweep err: %v", err)
|
|
}
|
|
close(out)
|
|
|
|
var findings []recon.Finding
|
|
for f := range out {
|
|
findings = append(findings, f)
|
|
}
|
|
// Should match the two Go module paths, not /about, /search, or external links
|
|
if len(findings) != 2 {
|
|
t.Fatalf("expected 2 findings, got %d", len(findings))
|
|
}
|
|
|
|
want1 := srv.URL + "/github.com/example/openai-go"
|
|
want2 := srv.URL + "/github.com/test/llm-client"
|
|
got := map[string]bool{}
|
|
for _, f := range findings {
|
|
got[f.Source] = true
|
|
if f.SourceType != "recon:goproxy" {
|
|
t.Errorf("unexpected SourceType: %s", f.SourceType)
|
|
}
|
|
}
|
|
if !got[want1] || !got[want2] {
|
|
t.Fatalf("missing expected sources; got=%v", got)
|
|
}
|
|
if hits == 0 {
|
|
t.Fatal("server was never hit")
|
|
}
|
|
}
|
|
|
|
func TestGoProxy_NameAndRate(t *testing.T) {
|
|
s := &GoProxySource{}
|
|
if s.Name() != "goproxy" {
|
|
t.Errorf("unexpected name: %s", s.Name())
|
|
}
|
|
if s.Burst() != 2 {
|
|
t.Errorf("burst: %d", s.Burst())
|
|
}
|
|
if s.RespectsRobots() {
|
|
t.Error("expected RespectsRobots=false")
|
|
}
|
|
}
|
|
|
|
func TestGoProxy_EnabledAlwaysTrue(t *testing.T) {
|
|
s := &GoProxySource{}
|
|
if !s.Enabled(recon.Config{}) {
|
|
t.Fatal("expected Enabled=true")
|
|
}
|
|
}
|
|
|
|
func TestGoProxy_Sweep_CtxCancelled(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
time.Sleep(500 * time.Millisecond)
|
|
_, _ = w.Write([]byte(goProxyFixtureHTML))
|
|
}))
|
|
defer srv.Close()
|
|
|
|
src := newGoProxyTestSource(srv.URL)
|
|
ctx, cancel := context.WithCancel(context.Background())
|
|
cancel()
|
|
|
|
out := make(chan recon.Finding, 4)
|
|
if err := src.Sweep(ctx, "", out); err == nil {
|
|
t.Fatal("expected ctx error")
|
|
}
|
|
}
|