tihao-ai/claude-code-tihao-sourcing/scripts/leak-mojibake-audit.js

#!/usr/bin/env node
const fs = require('fs');
const path = require('path');

const ROOT = path.resolve(__dirname, '..');
const DEFAULT_TARGETS = [
  'package.json',
  'README.md',
  'install.js',
  'bin',
  'skill-package-manifest.json',
  '.mcp.json',
  '.claude-plugin',
  'memory-templates',
  'docs',
  'scripts',
  path.join('mcp', 'src'),
  'skills',
  'fixtures'
];
const SECRET_PATTERNS = [
  { name: 'openai-style-key', regex: new RegExp('sk-' + '[A-Za-z0-9_-]{20,}', 'g') },
  { name: 'parse-session-token', regex: new RegExp('r:' + '[A-Za-z0-9]{20,}', 'g') },
  { name: 'authorization-bearer', regex: new RegExp('Authorization\\s*[:=]\\s*Bearer\\s+[A-Za-z0-9._-]{16,}', 'gi') }
];
const MOJIBAKE_PATTERNS = [
  { name: 'replacement-char', regex: /\uFFFD/g },
  { name: 'common-mojibake-1', regex: /é”|鈥|涓|乣/g },
  { name: 'common-mojibake-2', regex: /缂栧彿|鎺掑悕|鍗氫富|瀹㈡埛|褰掑洜|杞欢|寮烘帹/g },
  { name: 'utf8-read-as-gbk-short', regex: /[鎻绛鏍鍙瑙璇鐩杈閫浼缂鏂鍟氫涔乣]{3,}/g },
  { name: 'utf8-read-as-gbk-punctuation', regex: /[銆乣鈥滐紝]/g }
];
const SELF = path.normalize(__filename);

function main() {
  const args = parseArgs(process.argv.slice(2));
  const targets = args.targets ? String(args.targets).split(',').filter(Boolean) : DEFAULT_TARGETS;
  const files = targets.flatMap(target => listFiles(path.resolve(ROOT, target)));
  const hits = [];
  for (const file of files) {
    if (shouldSkip(file)) continue;
    const text = fs.readFileSync(file, 'utf8');
    for (const pattern of [...SECRET_PATTERNS, ...MOJIBAKE_PATTERNS]) {
      const matches = [...text.matchAll(pattern.regex)];
      for (const match of matches) hits.push(toHit(file, text, pattern.name, match));
    }
  }

  const summary = {
    root: ROOT,
    scannedFiles: files.filter(file => !shouldSkip(file)).length,
    hitCount: hits.length,
    hits
  };

  if (args.output) {
    fs.mkdirSync(path.dirname(path.resolve(args.output)), { recursive: true });
    fs.writeFileSync(path.resolve(args.output), JSON.stringify(summary, null, 2), 'utf8');
  }

  console.log(JSON.stringify({
    scannedFiles: summary.scannedFiles,
    hitCount: summary.hitCount,
    hits: summary.hits.slice(0, 20)
  }, null, 2));

  if (summary.hitCount) process.exitCode = 1;
}

function shouldSkip(file) {
  const normalized = path.normalize(file);
  return normalized === SELF ||
    /[\\/]node_modules[\\/]/.test(normalized) ||
    /[\\/]\.claude[\\/]/.test(normalized) ||
    /[\\/]\.npm-cache/.test(normalized);
}

function toHit(file, text, pattern, match) {
  const index = match.index || 0;
  const lineNumber = text.slice(0, index).split(/\r?\n/).length;
  const line = text.split(/\r?\n/)[lineNumber - 1] || '';
  return {
    file: path.relative(ROOT, file).replace(/\\/g, '/'),
    lineNumber,
    pattern,
    sample: maskSecret(match[0]),
    line: maskSecret(line).slice(0, 240)
  };
}

function maskSecret(value) {
  return String(value || '')
    .replace(new RegExp('sk-' + '([A-Za-z0-9_-]{4})[A-Za-z0-9_-]{8,}([A-Za-z0-9_-]{4})', 'g'), 'sk-$1...$2')
    .replace(new RegExp('r:' + '([A-Za-z0-9]{4})[A-Za-z0-9]{8,}([A-Za-z0-9]{4})', 'g'), 'r:$1...$2')
    .replace(/Bearer\s+([A-Za-z0-9._-]{4})[A-Za-z0-9._-]{8,}([A-Za-z0-9._-]{4})/gi, 'Bearer $1...$2');
}

function listFiles(target) {
  if (!fs.existsSync(target)) return [];
  const stat = fs.statSync(target);
  if (stat.isFile()) return [target];
  return fs.readdirSync(target, { withFileTypes: true }).flatMap(entry => {
    const full = path.join(target, entry.name);
    return entry.isDirectory() ? listFiles(full) : [full];
  });
}

function parseArgs(argv) {
  const args = {};
  for (let index = 0; index < argv.length; index += 1) {
    const raw = argv[index];
    if (!raw.startsWith('--')) continue;
    const key = raw.slice(2).replace(/-([a-z])/g, (_, char) => char.toUpperCase());
    const next = argv[index + 1];
    if (!next || next.startsWith('--')) args[key] = true;
    else {
      args[key] = next;
      index += 1;
    }
  }
  return args;
}

if (require.main === module) main();

module.exports = {
  listFiles,
  maskSecret
};