#!/usr/bin/env python3 """Поиск секретов в текстовых файлах внутри архива.""" from __future__ import annotations import argparse import json import re import tarfile import zipfile from pathlib import Path TEXT_EXTENSIONS = { ".txt", ".md", ".rst", ".log", ".csv", ".json", ".jsonl", ".yaml", ".yml", ".ini", ".cfg", ".conf", ".config", ".env", ".properties", ".toml", ".xml", ".sh", ".bash", ".zsh", ".py", ".js", ".ts", ".tsx", ".jsx", ".go", ".rs", ".java", ".php", ".rb", ".sql", ".html", ".css", ".ps1", ".bat", } PATTERNS = [ ("private-key", re.compile(r"-----BEGIN (?:RSA |EC |OPENSSH |DSA )?PRIVATE KEY-----"), 0), ("aws-access-key", re.compile(r"\bAKIA[0-9A-Z]{16}\b"), 0), ("bearer-token", re.compile(r"(?i)\bbearer\s+[A-Za-z0-9._~+/-]{12,}"), 0), ("password", re.compile(r"(?i)\b(?:password|passwd|pwd)\b\s*[:=]\s*['\"]?([^\s'\"]{4,})"), 1), ("api-key", re.compile(r"(?i)\b(?:api[_-]?key|secret[_-]?key|access[_-]?token|auth[_-]?token)\b\s*[:=]\s*['\"]?([^\s'\"]{4,})"), 1), ("connection-string", re.compile(r"(?i)\b(?:postgres|mysql|mongodb|redis)://[^\s:@]+:[^\s@]+@"), 0), ] def mask(value: str) -> str: value = value.strip() if len(value) <= 4: return "*" * len(value) return value[:2] + "*" * min(len(value) - 4, 16) + value[-2:] def inspect_text(name: str, text: str) -> list[dict]: findings = [] for number, line in enumerate(text.splitlines(), 1): for kind, pattern, group in PATTERNS: for match in pattern.finditer(line): value = match.group(group) if group else match.group(0) findings.append({"file": name, "line": number, "kind": kind, "preview": mask(value)}) return findings def is_text(name: str) -> bool: return Path(name).suffix.lower() in TEXT_EXTENSIONS def main() -> int: parser = argparse.ArgumentParser(description="Найти секреты внутри архива") parser.add_argument("archive", type=Path, help="Zip или tar архив") parser.add_argument("--max-size", type=int, default=1024 * 1024, help="Максимальный размер проверяемого файла") parser.add_argument("--json", type=Path, help="Сохранить отчёт в JSON") parser.add_argument("--fail-on-found", action="store_true", help="Вернуть код 2 при находках") args = parser.parse_args() path = args.archive.expanduser().resolve() if not path.is_file(): parser.error(f"Архив не найден: {path}") findings: list[dict] = [] skipped: list[str] = [] if zipfile.is_zipfile(path): with zipfile.ZipFile(path) as archive: for info in archive.infolist(): if info.is_dir() or not is_text(info.filename) or info.file_size > args.max_size: continue if info.flag_bits & 0x1: skipped.append(f"{info.filename}: зашифрован") continue try: with archive.open(info) as handle: data = handle.read(args.max_size + 1) except (RuntimeError, zipfile.BadZipFile) as error: skipped.append(f"{info.filename}: {error}") continue if b"\x00" in data[:1024]: continue findings.extend(inspect_text(info.filename, data.decode("utf-8", errors="replace"))) elif tarfile.is_tarfile(path): with tarfile.open(path, mode="r:*") as archive: for member in archive: if not member.isfile() or not is_text(member.name) or member.size > args.max_size: continue source = archive.extractfile(member) if source is None: continue with source: data = source.read(args.max_size + 1) if b"\x00" in data[:1024]: continue findings.extend(inspect_text(member.name, data.decode("utf-8", errors="replace"))) else: print("Формат не распознан. Поддерживаются zip и tar.") return 2 for item in skipped: print(f"Пропуск: {item}") for item in findings: print(f"{item['file']}:{item['line']}: {item['kind']} -> {item['preview']}") if not findings: print("Подозрительных строк не найдено.") else: print(f"Находок: {len(findings)}. Значения замаскированы.") if args.json: args.json.write_text( json.dumps({"archive": str(path), "findings": findings, "skipped": skipped}, ensure_ascii=False, indent=2), encoding="utf-8", ) if findings and args.fail_on_found: return 2 return 0 if __name__ == "__main__": raise SystemExit(main())