Researchers Find 175,000 Publicly Exposed Ollama AI Servers Across 130 Countries
Summary: A joint investigation by SentinelOne SentinelLABS and Censys found 175,000 unique Ollama hosts exposed across 130 countries, operating outside the guardrails and monitoring that platform providers apply by default. Just over 30% of the exposures are in China, and more than 48% of observed hosts advertise tool-calling capabilities that let them execute code, access APIs, and interact with external systems.
Key Takeaway: A tool-enabled endpoint can execute privileged operations rather than just produce text, and researchers call the combination of insufficient authentication and network exposure the highest-severity risk in the ecosystem - with 201 hosts already running uncensored prompt templates that strip safety guardrails.
Read the original at The Hacker News ↗
- Topics
- AI Security
- Related
- SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 8 Cyber Risks · Nov 15, 2026Pentagon Renames CDAO ‘Super Intelligence Office’ Cyber Risks · Nov 15, 2026186 Fake AI Domains Redirect Users to Click Fix Lures, Browser Malware, and Search Hijackers Cyber Risks · Nov 12, 2026