8 Commits
1.3 ... 1.6

Author SHA1 Message Date
ben
875747ad7a Add zipany format. v1.6 2018-09-29 23:37:54 +02:00
ben
200508be7f Fix PDF offset with acrobat-compatibility option. 2018-09-29 22:04:05 +02:00
ben
fc7e44a646 Rename pdfraw to pdfany and allow 2 payloads. v1.5.2 2018-09-29 14:06:08 +02:00
ben
04eb07f321 Fix help message 2018-09-29 00:17:53 +02:00
ben
caaaaafeb0 Add pdfraw format, v1.5 2018-09-29 00:12:49 +02:00
ben
7e962d60ad Add acrobat reader compatibility for szipdf format 2018-09-28 22:55:53 +02:00
ben
79ddd879c3 Change README 2018-09-28 22:24:40 +02:00
ben
3111008246 Clean source, remove website from src. 2018-09-28 22:21:03 +02:00
34 changed files with 161 additions and 422 deletions

View File

@@ -2,6 +2,8 @@
# -*- coding: utf-8 -*-
from .polyglotpdfzip import PolyglotPdfZip
from .polyglotpdfany import PolyglotPdfAny
from .polyglotzippdf import PolyglotZipPdf
from .polyglotszippdf import PolyglotSZipPdf
from .polyglotzipany import PolyglotZipAny

View File

@@ -0,0 +1,49 @@
# -*- coding: utf-8 -*-
import logging
'''
|-------------------------------| -
|--------- PDF Header ----------K1 | J1
|-------------------------------| -
|---- PDF OBJ 1 = Payload 1 ----K2 |
|-------------------------------| -
|---- Original PDF Ojbects -----K3 | J2
|-------------------------------| -
|-- PDF Last OBJ = Payload 2 ---K4 |
|-------------------------------| |
|---------- Xref Table ---------| |
|-------------------------------K5 |
|----------- Trailer -----------| |
|-------------------------------| |
'''
class PolyglotPdfAny():
from PdfFileTransformer import Pdf
def __init__(self, Pdf, payload1filename, payload2filename):
self.buffer = bytearray()
self.pdf = Pdf
self.payload1 = bytearray()
if payload1filename is not None:
with open(payload1filename, "rb") as f:
self.payload1 = f.read()
self.payload2 = bytearray()
if payload2filename is not None:
with open(payload2filename, "rb") as f:
self.payload2 = f.read()
def generate(self):
k2stream = self.payload1
if len(k2stream) > 0:
self.pdf.insert_new_obj_stream_at_start(k2stream)
k4stream = self.payload2
if len(k4stream) > 0:
self.pdf.insert_new_obj_stream_at_end(k4stream)
self.buffer = self.pdf.get_build_buffer()
def write(self, filename):
fd = open(filename, "wb")
fd.write(self.buffer)
fd.close()

View File

@@ -28,8 +28,9 @@ from PdfFileTransformer import Pdf
class PolyglotSZipPdf(PolyglotPdfZip):
def __init__(self, Pdf, Zip):
def __init__(self, Pdf, Zip, acrobat_compatibility):
super().__init__(Pdf, Zip)
self.acrobat_compatibility = acrobat_compatibility
def get_rebuild_zip_first_part_size(self):
@@ -80,9 +81,15 @@ class PolyglotSZipPdf(PolyglotPdfZip):
k2_stream_offset = new_pdf.get_first_stream_offset()
new_pdf.file_offset = offset
if self.acrobat_compatibility:
new_pdf.file_offset = new_pdf.file_offset + 1
pdf_buffer = new_pdf.get_build_buffer()
j2 = pdf_buffer[k2_stream_offset + size_k2_stream:]
new_zip.add_data_to_file(b'', j2, True)
if self.acrobat_compatibility:
new_zip.add_data_to_file(b'\x00', j2, True)
else:
new_zip.add_data_to_file(b'', j2, True)
return new_zip.buffer

View File

@@ -0,0 +1,42 @@
# -*- coding: utf-8 -*-
import logging
'''
|-------------------------------| -
|---------- Payload 1 ----------K1 | J1
|-------------------------------| -
|---- ZIP Local File Header ----K2 |
|-------------------------------| -
|---------- Payload 2-----------K3 | J2
|-------------------------------| -
|---- ZIP Central Directory ----K4 |
|-------------------------------| |
|--- End of Central Directory --K5 |
|-------------------------------| |
'''
class PolyglotZipAny():
from ZipFileTransformer import Zip
def __init__(self, Zip, payload1filename, payload2filename):
self.buffer = bytearray()
self.zip = Zip
self.payload1 = bytearray()
if payload1filename is not None:
with open(payload1filename, "rb") as f:
self.payload1 = f.read()
self.payload2 = bytearray()
if payload2filename is not None:
with open(payload2filename, "rb") as f:
self.payload2 = f.read()
def generate(self):
self.zip.add_data_to_file(self.payload1, self.payload2, True)
self.buffer = self.zip.buffer
def write(self, filename):
fd = open(filename, "wb")
fd.write(self.buffer)
fd.close()

View File

@@ -1,3 +1,3 @@
# TruePolyglot
# TruePolyglot #
See webiste at https://truepolyglot.hackade.org
[website](https://truepolyglot.hackade.org)

BIN
caradoc

Binary file not shown.

View File

@@ -23,6 +23,10 @@ EXAMPLES
# see https://github.com/mstamy2/PyPDF2/LICENSE
from __future__ import print_function
import sys
sys.path.append("../")
import argparse
from PdfFileTransformer.PyPDF2.pagerange import PAGE_RANGE_HELP

View File

@@ -6,7 +6,12 @@ import logging
from PdfFileTransformer import Pdf
from ZipFileTransformer import Zip
from PolyglotFile import PolyglotZipPdf, PolyglotPdfZip, PolyglotSZipPdf
from PolyglotFile import PolyglotZipPdf
from PolyglotFile import PolyglotPdfZip
from PolyglotFile import PolyglotSZipPdf
from PolyglotFile import PolyglotPdfAny
from PolyglotFile import PolyglotZipAny
def main():
@@ -16,10 +21,18 @@ def main():
'* zippdf: Generate a file valid as ZIP and PDF.' +
' The format is closest to ZIP.\n' +
'* szippdf: Generate a file valid as ZIP and PDF.' +
' The format is strictly a ZIP.' +
' Archive is modified.')
' The format is strictly a ZIP.\n' +
' Archive is modified.\n' +
'* pdfany: Generate a valid PDF file with payload1' +
' file content as first object\n' +
' or/and payload2 file' +
' content as last oject.\n' +
'* zipany: Generate a valid ZIP file with payload1' +
' file content at start of file\n' +
' or/and payload2 file content beetween' +
' LFH and CD.\n')
usage_str = '%(prog)s format [options] output-file'
epilog_str = 'TruePolyglot v1.3'
epilog_str = 'TruePolyglot v1.6'
frm = argparse.RawTextHelpFormatter
parser = argparse.ArgumentParser(description=description_str,
epilog=epilog_str,
@@ -27,14 +40,24 @@ def main():
formatter_class=frm)
parser.add_argument('format', nargs='+', choices=["pdfzip",
"zippdf",
"szippdf"],
"szippdf",
"pdfany",
"zipany"],
help='Output polyglot format')
parser.add_argument('--pdffile', dest='pdffile',
help='PDF input file')
parser.add_argument('--zipfile', dest='zipfile',
help='ZIP input file')
parser.add_argument('--payload1file', dest='payload1file',
help='Payload 1 input file')
parser.add_argument('--payload2file', dest='payload2file',
help='Payload 2 input file')
parser.add_argument('--acrobat-compatibility',
dest='acrobat_compatibility',
help='Add a byte at start for Acrobat Reader compatibility with szippdf format',
action='store_true')
parser.add_argument('--verbose', dest='verbose',
help='Verbosity level (default: debug)',
help='Verbosity level (default: info)',
default="info",
choices=["none", "error", "info", "debug"])
parser.add_argument('output_file', nargs='+',
@@ -42,12 +65,15 @@ def main():
args = parser.parse_args()
formats = ["pdfzip", "zippdf", "szippdf"]
if args.format[0] in formats:
if args.pdffile is None:
parser.error('pdffile is required')
if args.zipfile is None:
parser.error('zipfile is required')
if args.acrobat_compatibility and args.format[0] != "szippdf":
parser.error('--acrobat-compatibility is for szippdf only')
if "pdf" in args.format[0] and args.pdffile is None:
parser.error('pdffile is required')
if "zip" in args.format[0] and args.zipfile is None:
parser.error('zipfile is required')
if ("any" in args.format[0] and args.payload1file is None and
args.payload2file is None):
parser.error('payload1file or payload2file is required')
if args.verbose == "none":
logging.basicConfig(level=logging.CRITICAL)
@@ -58,14 +84,26 @@ def main():
if args.verbose == "debug":
logging.basicConfig(level=logging.DEBUG)
p = Pdf(args.pdffile)
z = Zip(args.zipfile)
if args.format[0] == "pdfzip":
p = Pdf(args.pdffile)
z = Zip(args.zipfile)
a = PolyglotPdfZip(p, z)
if args.format[0] == "zippdf":
p = Pdf(args.pdffile)
z = Zip(args.zipfile)
a = PolyglotZipPdf(p, z)
if args.format[0] == "szippdf":
a = PolyglotSZipPdf(p, z)
p = Pdf(args.pdffile)
z = Zip(args.zipfile)
a = PolyglotSZipPdf(p, z, args.acrobat_compatibility)
if args.format[0] == "pdfany":
p = Pdf(args.pdffile)
a = PolyglotPdfAny(p, args.payload1file, args.payload2file)
if args.format[0] == "zipany":
z = Zip(args.zipfile)
a = PolyglotZipAny(z, args.payload1file, args.payload2file)
a.generate()
a.write(args.output_file[0])

View File

@@ -1,63 +0,0 @@
html {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
body {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
td {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
th {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
h1 {
color: white;
}
a:link {
color: #47B8C7;
}
a:visited {
color: #47B8C7;
}
a:active {
color: #47B8C7;
}
table {
border-collapse: collapse;
}
table, th, td {
border: 1px solid white;
}
th {
background-color: #92D050;
color: black;
}
th {
padding-left: 0.5em;
padding-right: 0.5em;
padding-top: 0.5em;
padding-bottom: 0.5em;
}
td {
padding-left: 0.5em;
padding-right: 0.5em;
padding-bottom: 0.5em;
padding-top: 0.5em;
text-align: left;
}
.font_reduce {
font-size: 75%;
}
.warning {
color: #ffb833;
}

View File

@@ -1,61 +0,0 @@
html {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
body {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
td {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
th {
background-color: black;
font-family: Consolas,monaco,monospace;
color: #92D050;
}
a:link {
color: #47B8C7;
}
a:visited {
color: #47B8C7;
}
a:active {
color: #47B8C7;
}
table {
border-collapse: collapse;
}
table, th, td {
border: 1px solid white;
}
th {
background-color: #92D050;
color: black;
}
th {
padding-left: 0.5em;
padding-right: 0.5em;
padding-top: 0.5em;
padding-bottom: 0.5em;
}
td {
padding-left: 0.5em;
padding-right: 0.5em;
padding-bottom: 0.5em;
padding-top: 0.5em;
text-align: left;
}
th a:link {
color: black;
}
th a:visited {
color: black;
}
th a:active {
color: black;
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 318 B

View File

@@ -1,21 +0,0 @@
#!/bin/bash
find -type f -name 'polyglot.pdf' -delete
mkdir -p ./samples/pdfzip/poc1/
../truepolyglot pdfzip --pdffile ./samples/pdfzip/poc1/doc.pdf --zipfile ./samples/pdfzip/poc1/archive.zip ./samples/pdfzip/poc1/polyglot.pdf
mkdir -p ./samples/pdfzip/poc2/
../truepolyglot pdfzip --pdffile ./samples/pdfzip/poc2/orwell_1984.pdf --zipfile ./samples/pdfzip/poc2/file-FILE5_32.zip ./samples/pdfzip/poc2/polyglot.pdf
mkdir -p ./samples/pdfzip/poc3/
../truepolyglot pdfzip --pdffile ./samples/pdfzip/poc3/x86asm.pdf --zipfile ./samples/pdfzip/poc3/fasmw17304.zip ./samples/pdfzip/poc3/polyglot.pdf
mkdir -p ./samples/zippdf/poc4/
../truepolyglot zippdf --pdffile ./samples/zippdf/poc4/doc.pdf --zipfile ./samples/zippdf/poc4/archive.zip ./samples/zippdf/poc4/polyglot.pdf
mkdir -p ./samples/szippdf/poc5/
../truepolyglot szippdf --pdffile ./samples/szippdf/poc5/electronics.pdf --zipfile ./samples/szippdf/poc5/hello_world.jar ./samples/szippdf/poc5/polyglot.pdf
mkdir -p ./samples/pdfzip/poc6/
../truepolyglot pdfzip --pdffile ./samples/pdfzip/poc6/hexinator.pdf --zipfile ./samples/pdfzip/poc6/eicar.zip ./samples/pdfzip/poc6/polyglot.pdf

View File

@@ -1,251 +0,0 @@
<!doctype html>
<html lang="fr">
<head>
<meta charset="utf-8">
<title>TruePolyglot</title>
<meta name="description" content="TruePolyglot project website">
<meta name="author" content="hackade">
<link rel="stylesheet" href="css/styles.css">
<link rel="shortcut icon" href="/favicon.ico">
</head>
<body>
<h1>TruePolyglot</h1>
Truepolyglot is polyglot file generator project.
This means that the generated file is composed of several file formats. The same file can be opened as a ZIP file and as a PDF file for example.
The idea of this project comes from work of <a href="https://github.com/corkami">Ange Albertini</a>, <a href="https://www.alchemistowl.org/pocorgtfo/pocorgtfo07.pdf">International Journal of Proof-of-Concept or Get The Fuck Out</a> and <a href="https://www.troopers.de/wp-content/uploads/2011/04/TR11_Wolf_OMG_PDF.pdf">Julia Wolf</a> that explain how we can build a polyglot file.<br>
Polyglot file can be fastidious to build, even more if you want to respect correctly file format. That's why I decided to build a tool to generate them.<br>
My main motivation was the technical challenge.
<br>
<h2>Features and changelog</h2>
<div class="font_reduce">
<table>
<tr>
<th>Description</th>
<th>Version</th>
</tr>
<tr>
<td>Build a polyglot file valid as PDF and ZIP format and that can be opened with 7Zip and Windows Explorer</td>
<td>POC</td>
</tr>
<tr>
<td>Add a stream object in PDF part</td>
<td>POC</td>
</tr>
<tr>
<td>Polyglot file checked without warning with <a href="https://poppler.freedesktop.org/">pdftocairo</a></td>
<td> &gt;= 1.0</td>
</tr>
<tr>
<td>Polyglot file checked without warning with <a href="https://github.com/ANSSI-FR/caradoc">caradoc</a></td>
<td> &gt;= 1.0</td>
</tr>
<tr>
<td>Rebuild PDF Xref Table</td>
<td>&gt;= 1.0</td>
</tr>
<tr>
<td>Stream object with correct length header value</td>
<td>&gt;= 1.0</td>
</tr>
<tr>
<td>Format "zippdf", file without offset after Zip data</td>
<td>&gt;= 1.1</td>
</tr>
<tr>
<td>Polyglot file keep original PDF version</td>
<td>&gt;= 1.1.1</td>
</tr>
<tr>
<td>Add "szippdf" format without offset before and after Zip data</td>
<td>&gt;= 1.2</td>
</tr>
<tr>
<td>Fix /Length stream object value and PDF offset for szippdf format</td>
<td>&gt;= 1.2.1</td>
</tr>
<tr>
<td>PDF object numbers reorder after insertion</td>
<td>&gt;= 1.3</td>
</tr>
</table>
</div>
<h2>Polyglot file compatibility</h2>
<div class="font_reduce">
<table>
<tr>
<th>Software</th>
<th>Formats</th>
<th>status</th>
</tr>
<tr>
<td>Acrobat Reader</td>
<td>pdfzip, zippdf</td>
<td>OK</td>
</tr>
<tr>
<td>Acrobat Reader</td>
<td>szippdf</td>
<td><span class="warning">KO</span></td>
</tr>
<tr>
<td>Sumatra PDF</td>
<td>pdfzip, zippdf, szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>Edge</td>
<td>pdfzip, zippdf, szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>Firefox</td>
<td>pdfzip, zippdf, szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>7zip</td>
<td>pdfzip, zippdf</td>
<td><span class="warning">OK with warning</span></td>
</tr>
<tr>
<td>7zip</td>
<td>szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>Explorer Windows</td>
<td>pdfzip, zippdf, szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>Info-ZIP (unzip)</td>
<td>pdfzip, zippdf, szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>Evince</td>
<td>pdfzip, zippdf, szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>pdftocairo -pdf</td>
<td>pdfzip, zippdf, szippdf</td>
<td>OK</td>
</tr>
<tr>
<td>caradoc stats</td>
<td>pdfzip</td>
<td>OK</td>
</tr>
<tr>
<td>java</td>
<td>szippdf</td>
<td>OK</td>
</tr>
</table>
</div>
<h2>Examples</h2>
<ul>
<li><a href="/samples/">Polyglot files repository</a></li>
</ul>
<div class="font_reduce">
<table>
<tr>
<th>PDF input file</th>
<th>Zip input file</th>
<th>Format</th>
<th>Polyglot</th>
<th>Comment</th>
</tr>
<tr>
<td><a href="/samples/pdfzip/poc1/doc.pdf">doc.pdf</a></td>
<td><a href="/samples/pdfzip/poc1/archive.zip">archive.zip</a></td>
<td>pdfzip</td>
<td><a href="/samples/pdfzip/poc1/polyglot.pdf">polyglot.pdf</a></td>
<td>PDF/ZIP polyglot - 122 Ko</td>
</tr>
<tr>
<td><a href="/samples/pdfzip/poc2/orwell_1984.pdf">orwell_1984.pdf</a></td>
<td><a href="/samples/pdfzip/poc2/file-FILE5_32.zip">file-FILE5_32.zip</a></td>
<td>pdfzip</td>
<td><a href="/samples/pdfzip/poc2/polyglot.pdf">polyglot.pdf</a></td>
<td>PDF/ZIP polyglot - 1.3 Mo</td>
</tr>
<tr>
<td><a href="/samples/pdfzip/poc3/x86asm.pdf">x86asm.pdf</a></td>
<td><a href="/samples/pdfzip/poc3/fasmw17304.zip">fasmw17304.zip</a></td>
<td>pdfzip</td>
<td><a href="/samples/pdfzip/poc3/polyglot.pdf">polyglot.pdf</a></td>
<td>PDF/ZIP polyglot - 1.8 Mo</td>
</tr>
<tr>
<td><a href="/samples/zippdf/poc4/doc.pdf">doc.pdf</a></td>
<td><a href="/samples/zippdf/poc4/archive.zip">archive.zip</a></td>
<td>zippdf</td>
<td><a href="/samples/zippdf/poc4/polyglot.pdf">polyglot.pdf</a></td>
<td>PDF/ZIP polyglot - 112 Ko</td>
</tr>
<tr>
<td><a href="/samples/szippdf/poc5/electronics.pdf">electronics.pdf</a></td>
<td><a href="/samples/szippdf/poc5/hello_world.jar">hello_world.jar</a></td>
<td>szippdf</td>
<td><a href="/samples/szippdf/poc5/polyglot.pdf">polyglot.pdf</a></td>
<td>PDF/JAR polyglot - 778 Ko</td>
</tr>
<tr>
<td><a href="/samples/pdfzip/poc6/hexinator.pdf">hexinator.pdf</a></td>
<td><a href="/samples/pdfzip/poc6/eicar.zip">eicar.zip</a>&nbsp;(<a href="https://www.virustotal.com/#/file/2174e17e6b03bb398666c128e6ab0a27d4ad6f7d7922127fe828e07aa94ab79d/detection">scan virustotal.com</a>)</td>
<td>pdfzip</td>
<td><a href="/samples/pdfzip/poc6/polyglot.pdf">polyglot.pdf</a>&nbsp;(<a href="https://www.virustotal.com/#/file/f6fef31e3b03164bb3bdf35af0521f9fc0c518a9e0f1aa9f8b60ac936201591a/detection">scan virustotal.com</a>)</td>
<td>PDF/ZIP polyglot with Eicar test in Zip - 2.9 Mo</td>
</tr>
</table>
</div>
<h2>Manual</h2>
<pre>
usage: truepolyglot format [options] output-file
Generate a polyglot file.
Formats availables:
* pdfzip: Generate a file valid as PDF and ZIP. The format is closest to PDF.
* zippdf: Generate a file valid as ZIP and PDF. The format is closest to ZIP.
* szippdf: Generate a file valid as ZIP and PDF. The format is strictly a ZIP. Archive is modified.
positional arguments:
{pdfzip,zippdf,szippdf}
Output polyglot format
output_file Output polyglot file path
optional arguments:
-h, --help show this help message and exit
--pdffile PDFFILE PDF input file
--zipfile ZIPFILE ZIP input file
--verbose {none,error,info,debug}
Verbosity level (default: info)
TruePolyglot v1.3
</pre>
<h2>Code</h2>
<pre>
git clone <a href="https://git.hackade.org/truepolyglot.git/">https://git.hackade.org/truepolyglot.git/</a>
</pre>
<h2>Contact</h2>
On <a href="https://webchat.freenode.net/">IRC Freenode</a> my nickname is hackade or by mail at <a href="mailtp:truepolyglot@hackade.org">truepolyglot@hackade.org</a>.
</body>
</html>

View File

@@ -1,2 +0,0 @@
User-agent: *
Disallow: /

Binary file not shown.

Binary file not shown.

View File

@@ -1,3 +0,0 @@
#!/bin/bash
echo "http://127.0.0.1:8000"
python -m SimpleHTTPServer 8000

View File

@@ -1,2 +0,0 @@
#!/bin/bash
rsync -av --progress ./ -e ssh dragon:/var/www/html/truepolyglot/