Researchers Find 175,000 Publicly Exposed Ollama AI Servers Across 130 Countries (opens in new tab)

Covered by 3 sources including DEV Community, pulumi

Over 175,000 publicly exposed Ollama AI servers across 130 countries, with many enabling tool calling that allows code execution and LLMjacking abuse.

Read the original article

Sign in to keep reading the full article.

Sign Up Log In

Covered in 3 articles

DEV Community·

I parsed my own firewall logs and found which AI tools my org was really talking to — including one routing data to China

Discussed on DEV

pulumi·

Deploy a Private Hermes Agent on Render Securely with Pulumi, Modal, and Tailscale

Sysdig Blog·

Covered in 3 articles

I parsed my own firewall logs and found which AI tools my org was really talking to — including one routing data to China

Deploy a Private Hermes Agent on Render Securely with Pulumi, Modal, and Tailscale

LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools