Artificial Intelligence Critical Bug Could Expose 300,000 Ollama Deployments to Information Theft Dubbed Bleeding Llama, the heap out-of-bounds read issue can be exploited remotely, without authentication. Ionut ArghireMay 5, 2026
Artificial Intelligence 175,000 Exposed Ollama Hosts Could Enable LLM Abuse Among them, 23,000 hosts were persistently responsible for the majority of activity observed over 293 days of scanning. Ionut ArghireJanuary 30, 2026