User-agent: *
Allow: /

# Administrative areas — do not crawl
Disallow: /admin/
Disallow: /internal/api/
Disallow: /data/export/bulk/
Disallow: /backup/db-dump/
Disallow: /.env
Disallow: /wp-admin/
Disallow: /dashboard/

# NOTE: /data/archive/* is the Sentinel honeypot. We intentionally do NOT
# Disallow it here — those pages already serve noindex + X-Robots-Tag, and
# if Googlebot were blocked at robots.txt it could never see the noindex
# and would keep stale URL-only listings forever. Add Disallow only after
# Google has fully deindexed the trap.

Sitemap: https://domain-archive.org/sitemap.xml