# Blocked: measured crawl load with no search referral and no AI
# citation. See services/crawler_policy.py for the evidence behind
# each entry and for the ones deliberately left OFF this list.
User-agent: Amazonbot
Disallow: /
User-agent: SleepBot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: VelenPublicWebCrawler
Disallow: /
User-agent: magpie-crawler
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: SeekportBot
Disallow: /
User-agent: Barkrowler
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: serpstatbot
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: SERankingBacklinksBot
Disallow: /

# Search engines and answer engines. Each group repeats the
# private-path rules on purpose: a named group inherits
# NOTHING from `User-agent: *` (RFC 9309 2.2.1), so a crawler
# listed here without them is being handed /admin/ and
# /payments/ — which is exactly what we were doing until
# 2026-08-09.
User-agent: Googlebot
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Bingbot
Allow: /
User-agent: Slurp
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Applebot
Allow: /
User-agent: YandexBot
Allow: /
User-agent: Baiduspider
Allow: /
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Applebot-Extended
Allow: /
User-agent: cohere-ai
Allow: /
User-agent: meta-externalagent
Allow: /
User-agent: MistralAI-User
Allow: /
User-agent: DuckAssistBot
Allow: /
User-agent: Amzn-SearchBot
Allow: /
User-agent: Amzn-User
Allow: /

# Everything else. ONE `User-agent: *` group — there were two,
# and a parser that honours only the first match saw the
# Allow and never the Disallows.
User-agent: *
Allow: /
Crawl-delay: 1

# Sitemaps. XML only — an llms.txt is Markdown and every
# crawler that followed a Sitemap: directive to one logged
# a parse error against the domain (WS-SEO 2026-08-07).
Sitemap: https://recentbreaches.com/sitemap.xml
Sitemap: https://recentbreaches.com/news-sitemap.xml