feat(16-03): add RapidAPI recon source

- RapidAPISource searches public API listings for leaked keys
- Scrapes HTML search pages with ciLogKeyPattern matching
- Credentialless, httptest-based tests
This commit is contained in:
salvacybersec
2026-04-06 16:44:57 +03:00
parent edde02f3a2
commit 297ad3dc2b
2 changed files with 214 additions and 0 deletions

View File

@@ -0,0 +1,95 @@
package sources
import (
"context"
"fmt"
"io"
"net/http"
"net/url"
"time"
"golang.org/x/time/rate"
"github.com/salvacybersec/keyhunter/pkg/providers"
"github.com/salvacybersec/keyhunter/pkg/recon"
)
// RapidAPISource searches public RapidAPI listings for exposed API keys.
// API listings often include code snippets and example requests where
// developers may accidentally paste real credentials. Credentialless.
type RapidAPISource struct {
BaseURL string
Registry *providers.Registry
Limiters *recon.LimiterRegistry
Client *Client
}
var _ recon.ReconSource = (*RapidAPISource)(nil)
func (s *RapidAPISource) Name() string { return "rapidapi" }
func (s *RapidAPISource) RateLimit() rate.Limit { return rate.Every(3 * time.Second) }
func (s *RapidAPISource) Burst() int { return 3 }
func (s *RapidAPISource) RespectsRobots() bool { return false }
func (s *RapidAPISource) Enabled(_ recon.Config) bool { return true }
func (s *RapidAPISource) Sweep(ctx context.Context, query string, out chan<- recon.Finding) error {
base := s.BaseURL
if base == "" {
base = "https://rapidapi.com"
}
client := s.Client
if client == nil {
client = NewClient()
}
queries := BuildQueries(s.Registry, "rapidapi")
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
}
}
// Search RapidAPI public listings. The search page renders HTML with
// code examples and descriptions that may contain leaked keys.
searchURL := fmt.Sprintf(
"%s/search/%s?sortBy=ByRelevance&page=1",
base, url.PathEscape(q),
)
req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
if err != nil {
continue
}
resp, err := client.Do(ctx, req)
if err != nil {
continue
}
data, err := io.ReadAll(io.LimitReader(resp.Body, 512*1024))
_ = resp.Body.Close()
if err != nil {
continue
}
if ciLogKeyPattern.Match(data) {
out <- recon.Finding{
ProviderName: q,
Source: fmt.Sprintf("https://rapidapi.com/search/%s", url.PathEscape(q)),
SourceType: "recon:rapidapi",
Confidence: "low",
DetectedAt: time.Now(),
}
}
}
return nil
}

View File

@@ -0,0 +1,119 @@
package sources
import (
"context"
"net/http"
"net/http/httptest"
"testing"
"time"
"github.com/salvacybersec/keyhunter/pkg/providers"
"github.com/salvacybersec/keyhunter/pkg/recon"
)
func TestRapidAPI_Name(t *testing.T) {
s := &RapidAPISource{}
if s.Name() != "rapidapi" {
t.Fatalf("expected rapidapi, got %s", s.Name())
}
}
func TestRapidAPI_Enabled(t *testing.T) {
s := &RapidAPISource{}
if !s.Enabled(recon.Config{}) {
t.Fatal("RapidAPISource should always be enabled")
}
}
func TestRapidAPI_Sweep(t *testing.T) {
mux := http.NewServeMux()
mux.HandleFunc("/search/", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "text/html")
_, _ = w.Write([]byte(`<!DOCTYPE html>
<html>
<body>
<div class="api-listing">
<h2>OpenAI Helper API</h2>
<pre><code>
curl -H "Authorization: Bearer sk-proj-ABCDEF1234567890abcdef" https://api.example.com
api_key = "sk-proj-ABCDEF1234567890abcdef"
</code></pre>
</div>
</body>
</html>`))
})
srv := httptest.NewServer(mux)
defer srv.Close()
reg := providers.NewRegistryFromProviders([]providers.Provider{
{Name: "openai", Keywords: []string{"sk-proj-"}},
})
s := &RapidAPISource{
BaseURL: srv.URL,
Registry: reg,
Client: NewClient(),
}
out := make(chan recon.Finding, 10)
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
err := s.Sweep(ctx, "", out)
close(out)
if err != nil {
t.Fatalf("Sweep error: %v", err)
}
var findings []recon.Finding
for f := range out {
findings = append(findings, f)
}
if len(findings) == 0 {
t.Fatal("expected at least one finding from RapidAPI")
}
if findings[0].SourceType != "recon:rapidapi" {
t.Fatalf("expected recon:rapidapi, got %s", findings[0].SourceType)
}
}
func TestRapidAPI_Sweep_Clean(t *testing.T) {
mux := http.NewServeMux()
mux.HandleFunc("/search/", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "text/html")
_, _ = w.Write([]byte(`<!DOCTYPE html>
<html><body><p>No results found</p></body></html>`))
})
srv := httptest.NewServer(mux)
defer srv.Close()
reg := providers.NewRegistryFromProviders([]providers.Provider{
{Name: "openai", Keywords: []string{"sk-proj-"}},
})
s := &RapidAPISource{
BaseURL: srv.URL,
Registry: reg,
Client: NewClient(),
}
out := make(chan recon.Finding, 10)
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
err := s.Sweep(ctx, "", out)
close(out)
if err != nil {
t.Fatalf("Sweep error: %v", err)
}
var findings []recon.Finding
for f := range out {
findings = append(findings, f)
}
if len(findings) != 0 {
t.Fatalf("expected no findings, got %d", len(findings))
}
}