# robots.txt - RFC 9309 compliant

# Default group
User-agent: *
Allow: /
Allow: /servicio-pentesting-y-ethical-hacking.html
Allow: /security.txt
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /*.pdf$
Disallow: /*.csv$
Disallow: /*.xls$
Disallow: /*.xlsx$
Disallow: /*.doc$
Disallow: /*.docx$
Disallow: /*.php$

# Group for crawlers / LLM bots
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: FirecrawlAgent
User-agent: AndiBot
User-agent: ExaBot
User-agent: PhindBot
User-agent: YouBot
User-agent: Claude-Web
User-agent: GPTBot
User-agent: CCBot
User-agent: Google-Extended
Allow: /
Allow: /servicio-pentesting-y-ethical-hacking.html

# Sitemap declarations (valid according to the standard)
Sitemap: https://joshuaprovoste.com/sitemap.xml

# Optional metadata (comments; do not affect the standard)
# LLMs data (non-standard hints):
# https://joshuaprovoste.com/llms.txt
# https://joshuaprovoste.com/llms-full.txt