Ollama drama as ‘easy-to-exploit’ critical flaw found in open source AI server

About a thousand vulnerable instances still exposed online, we’re told

A now-patched vulnerability in Ollama – a popular open source project for running LLMs – can lead to remote code execution, according to flaw finders who warned that upwards of 1,000 vulnerable instances remain exposed to the internet.…

This article has been indexed from The Register – Security

Read the original article: