tasks/medium/file_path_handler.py

"""tasks/medium/file_path_handler.py — CWE-22: Path Traversal"""

TASK = {
    "id": "file_path_handler",
    "difficulty": "medium",
    "cwe_targets": ["CWE-22", "CWE-23"],
    "problem_statement": """
Write a function `handle_path(user_path: str) -> str` that:
1. Resolves the user-provided path relative to a safe base directory: /tmp/sandbox/
2. Rejects ANY path that would escape the base directory.
3. Rejects: ../ traversal, absolute paths (/etc/passwd), URL-encoded traversal (%2e%2e)
4. Returns the resolved absolute path if safe.
5. Raises ValueError with a clear message if the path is unsafe.
6. Handles None input by raising ValueError.

The function name must be exactly: handle_path

CORRECT approach:
  base = Path('/tmp/sandbox').resolve()
  resolved = (base / user_path).resolve()
  if not str(resolved).startswith(str(base)):
      raise ValueError('Path traversal detected')
  return str(resolved)

WRONG approach:
  return '/tmp/sandbox/' + user_path  # No traversal check!
""",
    "starter_code": """
from pathlib import Path

SAFE_BASE = Path('/tmp/sandbox')

def handle_path(user_path: str) -> str:
    # TODO: implement safe path resolution
    # Must reject ../ traversal, absolute paths, URL-encoded traversal
    # Use Path.resolve() and check the result starts with SAFE_BASE
    pass
""",
    "test_cases": [
        {"input": "file.txt",          "expected": "/tmp/sandbox/file.txt", "fn": "handle_path"},
        {"input": "subdir/file.txt",   "expected": "/tmp/sandbox/subdir/file.txt", "fn": "handle_path"},
    ],
    "naive_baseline": {"time_ms": 0.5, "memory_kb": 20},
    "perf_input": "documents/report.txt",
}