feat(14-03): implement SourceMapSource, WebpackSource, EnvLeakSource with tests

- SourceMapSource probes .map files for original source containing API keys
- WebpackSource scans JS bundles for inlined NEXT_PUBLIC_/REACT_APP_/VITE_ env vars
- EnvLeakSource probes common .env paths for exposed environment files
- All three implement ReconSource, credentialless, with httptest-based tests
This commit is contained in:
salvacybersec
2026-04-06 13:17:07 +03:00
parent dc90785ab0
commit b57bd5e7d9
6 changed files with 777 additions and 0 deletions

View File

@@ -0,0 +1,111 @@
package sources
import (
"context"
"fmt"
"io"
"net/http"
"regexp"
"time"
"golang.org/x/time/rate"
"github.com/salvacybersec/keyhunter/pkg/providers"
"github.com/salvacybersec/keyhunter/pkg/recon"
)
// EnvLeakSource probes for publicly accessible .env files on web servers.
// Many web frameworks (Laravel, Rails, Node/Express, Django) use .env files
// for configuration. Misconfigured servers frequently serve these files
// directly, exposing API keys and database credentials.
type EnvLeakSource struct {
BaseURL string
Registry *providers.Registry
Limiters *recon.LimiterRegistry
Client *Client
}
var _ recon.ReconSource = (*EnvLeakSource)(nil)
func (s *EnvLeakSource) Name() string { return "dotenv" }
func (s *EnvLeakSource) RateLimit() rate.Limit { return rate.Every(2 * time.Second) }
func (s *EnvLeakSource) Burst() int { return 2 }
func (s *EnvLeakSource) RespectsRobots() bool { return true }
func (s *EnvLeakSource) Enabled(_ recon.Config) bool { return true }
// envKeyValuePattern matches KEY=VALUE lines typical of .env files.
var envKeyValuePattern = regexp.MustCompile(`(?im)^[A-Z_]*(API[_]?KEY|SECRET|TOKEN|PASSWORD|CREDENTIALS?)[A-Z_]*\s*=\s*\S+`)
// envFilePaths are common locations for exposed .env files.
var envFilePaths = []string{
"/.env",
"/.env.local",
"/.env.production",
"/.env.development",
"/.env.backup",
"/.env.example",
"/app/.env",
"/api/.env",
}
func (s *EnvLeakSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
base := s.BaseURL
if base == "" {
return nil
}
client := s.Client
if client == nil {
client = NewClient()
}
queries := BuildQueries(s.Registry, "dotenv")
if len(queries) == 0 {
return nil
}
for _, q := range queries {
if err := ctx.Err(); err != nil {
return err
}
for _, path := range envFilePaths {
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
}
}
probeURL := fmt.Sprintf("%s%s", base, path)
req, err := http.NewRequestWithContext(ctx, http.MethodGet, probeURL, nil)
if err != nil {
continue
}
resp, err := client.Do(ctx, req)
if err != nil {
continue
}
body, err := io.ReadAll(io.LimitReader(resp.Body, 64*1024)) // 64KB max
_ = resp.Body.Close()
if err != nil {
continue
}
if envKeyValuePattern.Match(body) {
out <- recon.Finding{
ProviderName: q,
Source: probeURL,
SourceType: "recon:dotenv",
Confidence: "high",
DetectedAt: time.Now(),
}
}
}
}
return nil
}