4b268d109f
- NpmSource searches npm registry JSON API for provider keywords - PyPISource scrapes pypi.org search HTML for project links - Both credentialless, rate-limited at 1 req/2s, burst 2 - httptest-based tests verify Sweep, ctx cancellation, Name/Rate/Burst
134 lines
3.3 KiB
Go
134 lines
3.3 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 pypiTestRegistry() *providers.Registry {
|
|
return providers.NewRegistryFromProviders([]providers.Provider{
|
|
{Name: "openai", Keywords: []string{"sk-proj-"}},
|
|
})
|
|
}
|
|
|
|
const pypiFixtureHTML = `<!doctype html>
|
|
<html><body>
|
|
<a href="/project/openai-leaked/">openai-leaked</a>
|
|
<a href="/project/sk-proj-helper/">sk helper</a>
|
|
<a href="/simple/">nope</a>
|
|
<a href="https://external.example.com/project/nope/">external</a>
|
|
<a href="/project/openai-leaked/">duplicate</a>
|
|
</body></html>`
|
|
|
|
func newPyPITestSource(srvURL string) *PyPISource {
|
|
return &PyPISource{
|
|
BaseURL: srvURL,
|
|
Registry: pypiTestRegistry(),
|
|
Limiters: recon.NewLimiterRegistry(),
|
|
Client: NewClient(),
|
|
}
|
|
}
|
|
|
|
func TestPyPI_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(pypiFixtureHTML))
|
|
}))
|
|
defer srv.Close()
|
|
|
|
src := newPyPITestSource(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)
|
|
}
|
|
// 2 unique /project/ links (duplicate is deduped by extractAnchorHrefs)
|
|
if len(findings) != 2 {
|
|
t.Fatalf("expected 2 findings, got %d", len(findings))
|
|
}
|
|
|
|
got := map[string]bool{}
|
|
for _, f := range findings {
|
|
got[f.Source] = true
|
|
if f.SourceType != "recon:pypi" {
|
|
t.Errorf("unexpected SourceType: %s", f.SourceType)
|
|
}
|
|
if f.Confidence != "low" {
|
|
t.Errorf("unexpected Confidence: %s", f.Confidence)
|
|
}
|
|
}
|
|
if !got[srv.URL+"/project/openai-leaked/"] {
|
|
t.Error("missing openai-leaked finding")
|
|
}
|
|
if !got[srv.URL+"/project/sk-proj-helper/"] {
|
|
t.Error("missing sk-proj-helper finding")
|
|
}
|
|
if hits == 0 {
|
|
t.Fatal("server was never hit")
|
|
}
|
|
}
|
|
|
|
func TestPyPI_EnabledAlwaysTrue(t *testing.T) {
|
|
s := &PyPISource{}
|
|
if !s.Enabled(recon.Config{}) {
|
|
t.Fatal("expected Enabled=true")
|
|
}
|
|
}
|
|
|
|
func TestPyPI_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(pypiFixtureHTML))
|
|
}))
|
|
defer srv.Close()
|
|
|
|
src := newPyPITestSource(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")
|
|
}
|
|
}
|
|
|
|
func TestPyPI_NameAndRate(t *testing.T) {
|
|
s := &PyPISource{}
|
|
if s.Name() != "pypi" {
|
|
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")
|
|
}
|
|
want := float64(1) / 2
|
|
got := float64(s.RateLimit())
|
|
if got < want-0.01 || got > want+0.01 {
|
|
t.Errorf("rate limit=%v want~%v", got, want)
|
|
}
|
|
}
|