format

Signed-off-by: Hadi <[email protected]>

README.md

@@ -4,7 +4,7 @@
 
 <br>
 
-# GH-Recon
+# GH-Recon 🔍
 
 <p>
     <a href="https://github.com/anotherhadi/gh-recon/releases"><img src="https://img.shields.io/github/release/anotherhadi/gh-recon.svg" alt="Latest Release"></a>
@@ -12,11 +12,12 @@
     <a href="https://goreportcard.com/report/github.com/anotherhadi/gh-recon"><img src="https://goreportcard.com/badge/github.com/anotherhadi/gh-recon" alt="GoReportCard"></a>
 </p>
 
-## Project Overview
+## 🧾 Project Overview
 
-Fetches and aggregates public OSINT data for a GitHub user, leveraging Go and the GitHub API.
+Retrieves and aggregates public OSINT data about a GitHub user using Go and the GitHub API.
+Finds hidden emails in commit history, previous usernames, friends, other GitHub accounts, and more.
 
-## Features
+## 🚀 Features
 
 - Retrieve basic user profile information (username, ID, avatar, bio, creation dates)
 - List organizations and roles
@@ -28,16 +29,16 @@ Fetches and aggregates public OSINT data for a GitHub user, leveraging Go and th
 - Export results to JSON
 - Deep scan option (clone repositories, regex search, analyze licenses, etc.)
 
-## Disclaimer
+## ⚠️ Disclaimer
 
 This tool is intended for educational purposes only. Use responsibly and ensure you have permission to access the data you are querying.
 
-## Prerequisites
+## 📋 Prerequisites
 
 - Go 1.18+
 - GitHub Personal Access Token (recommended for higher rate limits): Create a GitHub API token with no permissions/no scope. This will be equivalent to public GitHub access, but it will allow access to use the GitHub Search API.
 
-## Installation
+## 📦 Installation
 
 ### With Go
 
@@ -74,7 +75,7 @@ environment.systemPackages = with pkgs; [ # or home.packages
 
 </details>
 
-## Usage
+## 🧪 Usage
 
 ```bash
 gh-recon --username TARGET_USER [--token YOUR_TOKEN]
@@ -95,7 +96,7 @@ gh-recon --username TARGET_USER [--token YOUR_TOKEN]
   -j, --json string           Write results to specified JSON file
 ```
 
-## Example
+## 💡 Examples
 
 ```bash
 gh-recon --username anotherhadi --token ghp_ABC123...
@@ -103,7 +104,7 @@ gh-recon --email [email protected]
 gh-recon --username anotherhadi --json output.json --deep
 ```
 
-## Cover your tracks
+## 🕵️‍♂️ Cover your tracks
 
 Understanding what information about you is publicly visible is the first step to managing your online presence. gh-recon can help you identify your own publicly available data on GitHub. Here’s how you can take steps to protect your privacy and security:
 
@@ -118,6 +119,6 @@ You can also use a tool like [TruffleHog](github.com/trufflesecurity/trufflehog)
 - [Blocking command line pushes that expose your personal email address](https://docs.github.com/en/account-and-profile/setting-up-and-managing-your-personal-account-on-github/managing-email-preferences/blocking-command-line-pushes-that-expose-your-personal-email-address)
 - [No-reply email address](https://docs.github.com/en/account-and-profile/setting-up-and-managing-your-personal-account-on-github/managing-email-preferences/setting-your-commit-email-address)
 
-## Contributing
+## 🤝 Contributing
 
 Feel free to contribute! See [CONTRIBUTING.md](CONTRIBUTING.md) for details.

gh-recon/deep.go

@@ -13,11 +13,10 @@ import (
 	"github.com/google/go-github/v72/github"
 )
 
-func folderExists(path string) bool {
-	if stat, err := os.Stat(path); err == nil && stat.IsDir() {
-		return true
-	}
-	return false
+type AuthorOccurrence struct {
+	Name    string
+	Email   string
+	FoundIn []string
 }
 
 type EmailOccurrence struct {
@@ -25,6 +24,19 @@ type EmailOccurrence struct {
 	FoundIn []string
 }
 
+type DeepResult struct {
+	Repositories []Repositorie
+	Authors      []AuthorOccurrence
+	Emails       []EmailOccurrence
+}
+
+type Repositorie struct {
+	Repository string
+	Owner      string
+	Name       string
+	Size       int
+}
+
 func findEmailsAndOccurrencesInDir(rootPath string) ([]EmailOccurrence, error) {
 	emailLocations := make(map[string]map[string]bool)
 	emailRegex := regexp.MustCompile(`[a-zA-Z0-9._%+\-]+@[a-zA-Z0-9.\-]+\.[a-zA-Z]{2,}`)
@@ -36,6 +48,9 @@ func findEmailsAndOccurrencesInDir(rootPath string) ([]EmailOccurrence, error) {
 			return err
 		}
 		if !d.IsDir() {
+			if strings.Contains(path, ".git/logs/") {
+				return nil
+			}
 			content, err := os.ReadFile(path)
 			if err != nil {
 				fmt.Printf("Can't read %s: %v\n", path, err)
@@ -78,14 +93,8 @@ func findEmailsAndOccurrencesInDir(rootPath string) ([]EmailOccurrence, error) {
 	return results, nil
 }
 
-type DeepResult struct {
-	Repository string
-	Owner      string
-	Name       string
-	Size       int
-}
-
-func (r Recon) Deep(username, excludeRepos string, refresh bool) (response []DeepResult) {
+func (r Recon) Deep(username, excludeRepos string, refresh bool) (response DeepResult) {
+	repositories := []Repositorie{}
 	excludeReposList := strings.Split(excludeRepos, ",")
 	repos, resp, err := r.Client.Repositories.ListByUser(
 		r.Ctx,
@@ -104,7 +113,28 @@ func (r Recon) Deep(username, excludeRepos string, refresh bool) (response []Dee
 		r.PrintInfo("INFO", "No repositories found")
 	} else {
 		for _, repo := range repos {
-			response = append(response, DeepResult{
+			if slices.Contains(excludeReposList, repo.GetName()) ||
+				slices.Contains(excludeReposList, repo.GetOwner().GetLogin()+"/"+repo.GetName()) {
+				continue
+			}
+
+			maxRepoSize := r.MaxRepoSize * 1024
+
+			if repo.GetSize() > maxRepoSize {
+				r.PrintInfo(
+					"INFO",
+					"Skipping repository "+repo.GetOwner().GetLogin()+"/"+repo.GetName()+" due to size", fmt.Sprintf(
+						"%d",
+						repo.GetSize()/1024,
+					)+"MB > "+fmt.Sprintf(
+						"%d",
+						maxRepoSize/1024,
+					)+"MB",
+				)
+				continue
+			}
+
+			repositories = append(repositories, Repositorie{
 				Repository: repo.GetCloneURL(),
 				Owner:      repo.GetOwner().GetLogin(),
 				Name:       repo.GetName(),
@@ -132,40 +162,19 @@ func (r Recon) Deep(username, excludeRepos string, refresh bool) (response []Dee
 		}
 	}
 
-	for _, repo := range response {
-		if slices.Contains(excludeReposList, repo.Name) ||
-			slices.Contains(excludeReposList, repo.Owner+"/"+repo.Name) {
-			r.PrintInfo("INFO", "Skipping repository", repo.Owner+"/"+repo.Name)
+	for _, repo := range repositories {
+		destination := tmp_folder + "/" + repo.Owner + "/" + repo.Name
+		if folderExists(destination) {
+			r.PrintInfo("INFO", "Directory already downloaded, skipping "+repo.Owner+"/"+repo.Name)
 			continue
 		}
 
-		maxRepoSize := r.MaxRepoSize * 1024
-
-		if repo.Size > maxRepoSize {
-			r.PrintInfo(
-				"INFO",
-				"Skipping repository "+repo.Owner+"/"+repo.Name+" due to size", fmt.Sprintf(
-					"%d",
-					repo.Size/1024,
-				)+"MB > "+fmt.Sprintf(
-					"%d",
-					maxRepoSize/1024,
-				)+"MB",
-			)
-			continue
-		}
 		r.PrintInfo(
 			"Downloading",
 			repo.Owner+"/"+repo.Name,
 			fmt.Sprintf("%d", repo.Size/1024)+"MB",
 		)
 
-		destination := tmp_folder + "/" + repo.Owner + "/" + repo.Name
-		if folderExists(destination) {
-			r.PrintInfo("INFO", "Directory already exists, skipping")
-			continue
-		}
-
 		cmd := exec.Command(
 			"git",
 			"clone",
@@ -187,22 +196,104 @@ func (r Recon) Deep(username, excludeRepos string, refresh bool) (response []Dee
 	}
 	r.PrintInfo("INFO", "Cloned all repositories to "+tmp_folder)
 
+	authorOccurrences := []AuthorOccurrence{}
+	mapAuthorToIndex := make(map[string]int)
+	for _, repo := range repositories {
+		destination := tmp_folder + "/" + repo.Owner + "/" + repo.Name
+		if !folderExists(filepath.Join(destination, ".git")) {
+			r.Logger.Error(
+				"No .git directory found, cannot run git log.",
+				"repo",
+				repo.Owner+"/"+repo.Name,
+				"path",
+				destination,
+			)
+		} else {
+			gitLogCmd := exec.Command("git", "log", "--all", "--format=%aN <%aE>")
+			gitLogCmd.Dir = destination
+			logOutput, logErr := gitLogCmd.Output()
+
+			if logErr != nil {
+				if exitErr, ok := logErr.(*exec.ExitError); ok {
+					r.Logger.Error("Failed to execute git log (ExitError)", "repo", repo.Owner+"/"+repo.Name, "stderr", string(exitErr.Stderr), "err", logErr)
+				} else {
+					r.Logger.Error("Failed to execute git log", "repo", repo.Owner+"/"+repo.Name, "err", logErr)
+				}
+			} else {
+				lines := strings.Split(string(logOutput), "\n")
+				repoIdentifier := repo.Owner + "/" + repo.Name
+
+				for _, line := range lines {
+					trimmedLine := strings.TrimSpace(line)
+					if trimmedLine == "" {
+						continue
+					}
+
+					if index, exists := mapAuthorToIndex[trimmedLine]; exists {
+						isRepoListed := false
+						for _, foundRepo := range authorOccurrences[index].FoundIn {
+							if foundRepo == repoIdentifier {
+								isRepoListed = true
+								break
+							}
+						}
+						if !isRepoListed {
+							authorOccurrences[index].FoundIn = append(authorOccurrences[index].FoundIn, repoIdentifier)
+							slices.Sort(authorOccurrences[index].FoundIn)
+						}
+					} else {
+						parts := strings.SplitN(trimmedLine, " <", 2)
+						var authorName, authorEmail string
+						if len(parts) == 2 {
+							authorName = parts[0]
+							authorEmail = strings.TrimSuffix(parts[1], ">")
+						} else if len(parts) == 1 {
+							authorName = "-"
+							authorEmail = strings.TrimPrefix(strings.TrimSuffix(parts[0], ">"), "<")
+						} else {
+							r.Logger.Error("Malformed author line from git log", "line", trimmedLine, "repo", repoIdentifier)
+							continue
+						}
+
+						authorOccurrences = append(authorOccurrences, AuthorOccurrence{
+							Name:    authorName,
+							Email:   authorEmail,
+							FoundIn: []string{repoIdentifier},
+						})
+						mapAuthorToIndex[trimmedLine] = len(authorOccurrences) - 1
+					}
+				}
+			}
+		}
+	}
+	for _, author := range authorOccurrences {
+		r.PrintInfo(
+			"Author",
+			author.Name+" <"+author.Email+">",
+			"found in:"+strings.Join(author.FoundIn, ", "),
+		)
+	}
+
 	r.PrintInfo("INFO", "Now searching for emails in cloned repositories, this may take a while...")
-	results, err := findEmailsAndOccurrencesInDir(tmp_folder)
+	emails, err := findEmailsAndOccurrencesInDir(tmp_folder)
 	if err != nil {
 		r.Logger.Error("Failed to find emails in directory", "err", err)
 		return
 	}
 
-	if len(results) == 0 {
+	if len(emails) == 0 {
 		r.PrintInfo("INFO", "No emails found")
 	} else {
 		r.PrintInfo("INFO", "Found emails:")
-		for _, email := range results {
+		for _, email := range emails {
 			r.PrintInfo("Email", email.Email, "found in:"+strings.Join(email.FoundIn, ", "))
 		}
 	}
 
+	response.Repositories = repositories
+	response.Authors = authorOccurrences
+	response.Emails = emails
+
 	r.PrintNewline()
 	return
 }

gh-recon/utils.go

@@ -165,3 +165,10 @@ func (r Recon) WriteJson(data any) {
 	}
 	r.PrintInfo("INFO", "JSON file created successfully", "file", r.JsonFile)
 }
+
+func folderExists(path string) bool {
+	if stat, err := os.Stat(path); err == nil && stat.IsDir() {
+		return true
+	}
+	return false
+}