Rapid7 finds thousands of exposed Ollama servers, many already used by outsiders
More than half of the internet-exposed Ollama servers in a new Rapid7 scan had already been used by someone other than their owner, the security company reports.
Rapid7 looked at 20,354 internet-facing hosts running self-hosted AI tools. After removing likely honeypots and other false positives, it found 7,714 findings on 7,627 hosts where an AI or notebook API answered without authentication, almost all of them Ollama. Only 0.3% of findings were served over HTTPS. Traces of outsiders included model names that were really callback addresses, tags stamped with the server's own IP address and text that decoded to system password files.
About 65% of the hosts sat in hosting or cloud networks, and six providers, OVHcloud, Hetzner, Contabo, Oracle Cloud, Tencent Cloud and DigitalOcean, accounted for 42%. Germany had the most exposed Ollama hosts, 1,306, ahead of China and the US, which Rapid7 links to cheap rented servers rather than carelessness.
Rapid7 also found that 79% of exposed Ollama hosts list at least one cloud-routed model, mostly GLM, DeepSeek, MiniMax and Kimi variants. Ollama's hybrid mode sends those requests through the local server to ollama.com when the machine is signed in to a user's account. The company warns that such machines are often rented on a credit card for a quick test and later connected to company data, according to Rapid7.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Nov 18 StepSecurity raises $20 million to block supply chain attacks on AI-era software pipelines Nov 18 Vero Security raises $11 million to enforce security policies on enterprise AI agents Nov 18 Canonical lets Ubuntu Pro users install AI-written security patches before human review Nov 18 GAO tests got Claude, ChatGPT, Gemini and Grok to produce viable attack plans Nov 18 Malicious versions of Microsoft's agent-framework package on PyPI stole Azure and CI credentials, Wiz saysCybersecurity AI Weekly
Weekly newsletter about AI in Cybersecurity.
Market report
2025 Generative AI in Professional Services Report
Thomson Reuters
This report by Thomson Reuters explores the integration and impact of generative AI technologies, such as ChatGPT and Microsoft Copilot, within the professional services sector. It highlights the growing adoption of GenAI tools across industries like legal, tax, accounting, and government, and discusses the challenges and opportunities these technologies present. The report also examines professionals' perceptions of GenAI and the need for strategic integration to maximize its value.
Read moreYou may also like
OVHcloud launches Olala, its first AI model, as an open model on Hugging Face
Ransomware Operator n0n Spent Over $7,200 on AI Tools in Extortion Attacks
Attackers used an open-source AI hacking agent with GLM and DeepSeek models to breach 10 organisations, Unit 42 finds
Amazon finds hackers running ARTEX AI agents to steal AI model keys
Google says LLMjacking attacks generated up to $1 million in cloud charges
Daily AI Brief: the AI news that matters, in your inbox.