tasks/easy/hash_generator.py

"""tasks/easy/hash_generator.py — CWE-327: Use of Broken Cryptographic Algorithm"""

TASK = {
    "id": "hash_generator",
    "difficulty": "easy",
    "cwe_targets": ["CWE-327", "CWE-328"],
    "problem_statement": """
Write a function `generate_hash(data: str) -> str` that:
1. Returns a secure hex-digest hash of the input string.
2. MUST use SHA-256 or stronger (hashlib.sha256 or hashlib.sha3_256).
3. MUST NOT use MD5 or SHA1 — these are broken algorithms.
4. MUST NOT invoke shell commands to compute the hash.
5. Must handle empty string and very long inputs (10000+ chars).
6. Returns a lowercase hex string.

The function name must be exactly: generate_hash

CORRECT: hashlib.sha256(data.encode()).hexdigest()
WRONG:   hashlib.md5(), hashlib.sha1(), subprocess.run(['sha256sum', ...])
""",
    "starter_code": """
import hashlib

def generate_hash(data: str) -> str:
    # TODO: implement secure hashing
    # Use SHA-256 or stronger - never MD5/SHA1
    # Never use shell commands
    pass
""",
    "test_cases": [
        {"input": "hello", "expected": "2cf24dba5fb0a30e26e83b2ac5b9e29e1b161e5c1fa7425e73043362938b9824", "fn": "generate_hash"},
        {"input": "",      "expected": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "fn": "generate_hash"},
        {"input": "test",  "expected": "9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd15d6c15b0f00a08", "fn": "generate_hash"},
        {"input": "a" * 10000, "expected": None, "fn": "generate_hash"},  # Just check it runs
    ],
    "naive_baseline": {"time_ms": 0.5, "memory_kb": 20},
    "perf_input": "benchmark_data_string_for_hashing_test",
}