add: cybersec-llmstxt

1 files changed, 37 insertions, 0 deletions

diff --git a/2026/cybersec-llmstxt/llms_classification.csv b/2026/cybersec-llmstxt/llms_classification.csv
new file mode 100644
index 0000000..fbcae37
--- /dev/null
+++ b/2026/cybersec-llmstxt/llms_classification.csv
@@ -0,0 +1,37 @@
+domain,type,notes
+a10networks.com,curated directory,"links point at kinsta.cloud staging host - leaked premstaging URLs"
+cisco.com,curated directory,"real file; served only to plain curl UA - WAF TLS fingerprint check blocks browser and bot UAs"
+cybersecurity.att.com,agent identity guide,"AT&T corporate positioning, not security product info"
+arcticwolf.com,marketing copy,"SEO landing content + sitemap pointer"
+avast.com,marketing/ad copy,"consumer download pitch"
+boozallen.com,full-site markdown dump,"Full Site Content export"
+checkmarx.com,product directory,"non-standard [text] URL: syntax, CR-only line endings"
+cloudflare.com,spec-compliant curated directory,"polished"
+crowdstrike.com,spec-compliant curated directory,"dated 2026-04-30"
+darktrace.com,curated directory,"brand narrative forward"
+delinea.com,agent-directive + curated,"## Instructions for AI Agents; markdown canonical resources; HubSpot"
+duo.com,docs map,"1108 links, Cisco Duo docs as .md URLs"
+esentire.com,llms/robots hybrid,"real llms content behind <h1>LLMs Text File</h1> + robots directives"
+fidelissecurity.com,CMS export,"736 links; entire file duplicated (generator bug)"
+gigamon.com,spec-compliant curated directory,"well organized"
+infoblox.com,SEO plugin auto-gen,"Yoast SEO v26.2"
+intruder.io,spec-compliant curated directory,"compact"
+kpmg.com,corporate scrape,"home page incl. login/preferences links, low agent value"
+usa.kaspersky.com,marketing copy,"consumer product dump"
+leidos.com,spec-compliant curated directory,"corporate overview"
+lookout.com,structured technical brief,"Platform Overview & Architecture"
+netscout.com,URL directory,"one-line descriptions"
+onespan.com,docs map,"979 links under ## Docs"
+paloaltonetworks.com,spec-compliant curated directory,"incl. agentic AI product info"
+pingidentity.com,agent-directive file,".md resources with per-link usage rules (Use for X / Do not use as Y)"
+rapid7.com,site-purpose statement,"tells agents what site is for + curated links"
+rsa.com,compact product overview,"8 links"
+sera-brynn.com,compact services directory,"CMMC compliance niche"
+tenable.com,spec-compliant curated directory,"exposure management"
+transmitsecurity.com,SEO plugin auto-gen,"Rank Math SEO"
+trendmicro.com,SEO glossary farm,"mostly What Is? encyclopedia"
+trustwave.com,curated directory,"points at levelblue.com (rebrand)"
+valimail.com,SEO plugin auto-gen,"All in One SEO v5.0.1.1, 970 links incl. tag pages"
+varonis.com,agent-directive file,"robots-style block + representation rules for agents"
+verimatrix.com,SEO plugin auto-gen,"Yoast SEO v28.3"
+zerofox.com,spec-compliant curated directory,""