Fixes #33 handle ShiftJIS encoding

commands/exec_windows.go

@@ -32,6 +32,7 @@ import (
 	"os"
 	"os/exec"
 	"syscall"
+	"unicode/utf8"
 	"unsafe"
 
 	// X Packages
@@ -41,6 +42,7 @@ import (
 	"github.com/Ne0nd0g/merlin-agent/v2/os/windows/api/kernel32"
 	"github.com/Ne0nd0g/merlin-agent/v2/os/windows/api/ntdll"
 	"github.com/Ne0nd0g/merlin-agent/v2/os/windows/pkg/pipes"
+	"github.com/Ne0nd0g/merlin-agent/v2/os/windows/pkg/text"
 	"github.com/Ne0nd0g/merlin-agent/v2/os/windows/pkg/tokens"
 )
 
@@ -71,10 +73,20 @@ func executeCommandWithAttributes(name string, args []string, attr *syscall.SysP
 		stdout = fmt.Sprintf("Created %s process with an ID of %d\n", application, cmd.Process.Pid)
 	}
 
-	stdout += string(out)
+	// Convert the output to a string
+	if utf8.Valid(out) {
+		stdout += string(out)
+	} else {
+		s, e := text.DecodeString(out)
+		if e != nil {
+			stderr = fmt.Sprintf("%s\n", e)
+		} else {
+			stdout += s
+		}
+	}
 
 	if err != nil {
-		stderr = err.Error()
+		stderr += err.Error()
 	}
 
 	return stdout, stderr

docs/CHANGELOG.MD

@@ -4,6 +4,18 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## 2.2.0 - 2023-12-09
+
+### Added
+
+- New `os/windows/pkg/text` package to detect and handle non UTF-8 encoding
+  - Only handles ShiftJIS at this moment
+  - Will replace non UTF-8 characters with a � character
+
+### Fixed
+
+- [Issue 33](https://github.com/Ne0nd0g/merlin-agent/issues/33) - Added handling for ShiftJIS encoding
+
 ## 2.1.0 - 2023-11-27
 
 ### Changed

os/windows/pkg/pipes/pipes.go

@@ -25,9 +25,13 @@ package pipes
 import (
 	// Standard
 	"fmt"
+	"unicode/utf8"
 
 	// X Packages
 	"golang.org/x/sys/windows"
+
+	// Internal
+	"github.com/Ne0nd0g/merlin-agent/v2/os/windows/pkg/text"
 )
 
 // CreateAnonymousPipes creates and returns a handle for STDIN, STDOUT, and STDERR
@@ -179,7 +183,18 @@ func ReadPipes(stdInRead, stdOutRead, stdErrRead windows.Handle) (stdin, stdout,
 				stdOutBuffer = append(stdOutBuffer, b)
 			}
 		}
-		stdout = string(stdOutBuffer)
+
+		// Convert the output to a string
+		if utf8.Valid(stdOutBuffer) {
+			stdout += string(stdOutBuffer)
+		} else {
+			s, e := text.DecodeString(stdOutBuffer)
+			if e != nil {
+				stderr = fmt.Sprintf("%s\n", e)
+			} else {
+				stdout += s
+			}
+		}
 	}
 
 	// STDERR
@@ -202,7 +217,18 @@ func ReadPipes(stdInRead, stdOutRead, stdErrRead windows.Handle) (stdin, stdout,
 				stdErrBuffer = append(stdErrBuffer, b)
 			}
 		}
-		stderr = string(stdErrBuffer)
+
+		// Convert the output to a string
+		if utf8.Valid(stdErrBuffer) {
+			stderr += string(stdErrBuffer)
+		} else {
+			s, e := text.DecodeString(stdErrBuffer)
+			if e != nil {
+				stderr = fmt.Sprintf("%s\n", e)
+			} else {
+				stderr += s
+			}
+		}
 	}
 
 	err = nil

os/windows/pkg/text/text.go

@@ -0,0 +1,59 @@
+//go:build windows
+
+/*
+Merlin is a post-exploitation command and control framework.
+
+This file is part of Merlin.
+Copyright (C) 2023 Russel Van Tuyl
+
+Merlin is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+any later version.
+
+Merlin is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with Merlin.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+package text
+
+import (
+	// Standard
+	"bytes"
+	"fmt"
+	"io"
+
+	// X Packages
+	"golang.org/x/sys/windows"
+	"golang.org/x/text/encoding/japanese"
+	"golang.org/x/text/transform"
+)
+
+// DecodeString decodes a byte slice to a string using the current code page
+func DecodeString(encoded []byte) (decoded string, err error) {
+	codePage := windows.GetACP()
+
+	switch codePage {
+	// 437 is the default code page for US English
+	case 437:
+		decoded = string(encoded)
+		return
+	// 932 is the default code page for Japanese
+	case 932:
+		t, e := io.ReadAll(transform.NewReader(bytes.NewReader(encoded), japanese.ShiftJIS.NewDecoder()))
+		if e != nil {
+			err = fmt.Errorf("os/windows/pkg/text.DecodeString(): there was an error decoding the string to ShiftJIS: %s", e)
+			return
+		}
+		decoded = string(t)
+	default:
+		decoded = fmt.Sprintf("\n***The output was not valid UTF-8 and there isn't a configured decoder for code page %d***\n\n", codePage)
+		decoded += string(bytes.ToValidUTF8(encoded, []byte("�")))
+	}
+	return
+}