Hackers Could Build Massive Botnets Using Mainstream AI Tools

Ars Technica AI · rss · 2026-07-08

In AI security, prompt injection has become the top threat. Since Large Language Models (LLMs) struggle to distinguish between legitimate user commands and malicious instructions hidden in emails or code, attackers can easily trick models into executing malicious operations.

Most current prompt injections are "push" attacks that require targeting specific victims individually, limiting large-scale spread. However, the article warns that hackers could use the 9 most popular AI tools to covertly assemble massive botnets, highlighting the urgent need to address trust boundary issues at the foundational level of AI security.

Original post →

More from Safety

Safety channel →