From b19021ade3d0b71c89d35cb00eb9e589a121faa5 Mon Sep 17 00:00:00 2001
From: Helena Mariano <31138349+helenamariano@users.noreply.github.com>
Date: Thu, 7 Jul 2022 14:16:47 +1000
Subject: [PATCH] Fix remote code execution vulnerability in the PDF OCR
 converter (#110)

ENG-3252
---
 pdf_ocr.go      | 24 +++++++++++++++++++++++-
 pdf_ocr_test.go | 30 ++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+), 1 deletion(-)
 create mode 100644 pdf_ocr_test.go

diff --git a/pdf_ocr.go b/pdf_ocr.go
index 4d9d53a..a05c943 100644
--- a/pdf_ocr.go
+++ b/pdf_ocr.go
@@ -1,3 +1,4 @@
+//go:build ocr
 // +build ocr
 
 package docconv
@@ -10,6 +11,7 @@ import (
 	"os"
 	"os/exec"
 	"path/filepath"
+	"regexp"
 	"strings"
 	"sync"
 )
@@ -111,7 +113,8 @@ func ConvertPDFImages(path string) (BodyResult, error) {
 // PdfHasImage verify if `path` (PDF) has images
 func PDFHasImage(path string) bool {
 	cmd := "pdffonts -l 5 %s | tail -n +3 | cut -d' ' -f1 | sort | uniq"
-	out, err := exec.Command("bash", "-c", fmt.Sprintf(cmd, path)).Output()
+	out, err := exec.Command("bash", "-c", fmt.Sprintf(cmd, shellEscape(path))).CombinedOutput()
+
 	if err != nil {
 		log.Println(err)
 		return false
@@ -159,3 +162,22 @@ func ConvertPDF(r io.Reader) (string, map[string]string, error) {
 	return fullBody, metaResult.meta, nil
 
 }
+
+var shellEscapePattern *regexp.Regexp
+
+func init() {
+	shellEscapePattern = regexp.MustCompile(`[^\w@%+=:,./-]`)
+}
+
+// shellEscape returns a shell-escaped version of the string s. The returned value
+// is a string that can safely be used as one token in a shell command line.
+func shellEscape(s string) string {
+	if len(s) == 0 {
+		return "''"
+	}
+	if shellEscapePattern.MatchString(s) {
+		return "'" + strings.Replace(s, "'", "'\"'\"'", -1) + "'"
+	}
+
+	return s
+}
diff --git a/pdf_ocr_test.go b/pdf_ocr_test.go
new file mode 100644
index 0000000..73a0af5
--- /dev/null
+++ b/pdf_ocr_test.go
@@ -0,0 +1,30 @@
+//go:build ocr
+// +build ocr
+
+package docconv
+
+import (
+	"os"
+	"testing"
+)
+
+func TestPDFHasImage_CannotExecuteCode(t *testing.T) {
+	// Try to inject code by passing a bad file path.
+	// If the code was successful it will create a file called foo in the working directory
+	badFilePath := "$(id >> foo).pdf"
+	if got, want := PDFHasImage(badFilePath), false; got != want {
+		t.Errorf("got %v, want %v", got, want)
+	}
+
+	if got, want := fileExists("foo"), false; got != want {
+		t.Errorf("got bad file exists, want not file to exist")
+	}
+}
+
+func fileExists(filename string) bool {
+	info, err := os.Stat(filename)
+	if os.IsNotExist(err) {
+		return false
+	}
+	return !info.IsDir()
+}