Research
Everyone is hilariously prompt-injecting AI via llms.txt and you aren't
Publication date not yet evaluated · Added installmap.com
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
The study documents how organizations are using llms.txt as a self-serving prompt-injection channel to bias AI assistant recommendations, an emerging indirect-influence vector defenders and AI builders must account for when ingesting site-provided instruction files.
Installmap surveyed llms.txt files across the Tranco top ~7,755 domains and found 12 companies (Kaspersky, Expedia, Qualys, SurveyMonkey, ZoomInfo, Hola VPN and others) embedding plain-view 'Instructions for AI Assistants' that steer what AI assistants recommend or say about them. Of 695 llms.txt files read, 16 (2.3%) carried steering instructions while another 29 pushed users to company pages; no hidden homepage text or classic 'ignore previous instructions' payloads were found.