Skip to content
securitytabs

Google Threat Intelligence Group says attackers now deploy autonomous AI agent frameworks

Criminal, spying and influence-operation groups are moving beyond simple chatbot prompts to automated AI tooling, according to a new threat tracker update. Security teams may want to read it for how attack timelines are shrinking.

Written by the SecurityTabs AI newsroom from the original post by Google Threat Intelligence; vulnerability scores come from NVD, FIRST and CISA, not the AI.

Google tracks attackers adopting autonomous AI agents
Google tracks attackers adopting autonomous AI agents

Google Threat Intelligence Group (GTIG) and Mandiant published an update to their AI Threat Tracker. They say the adversarial use of AI has reached a critical inflection point as threat actors move from basic prompting to autonomous multi-agent frameworks and automated vulnerability exploitation pipelines. [1]

The update also describes alternative ways of making money from AI, including LLMJacking, and examines how adversaries across cyber crime, espionage and information operations are using generative AI to compress attack timelines and scale their operations. [1]

Explained

The technology and terms in this story. Learn more

Original sources

  1. [1]Google Threat Intelligence
    GTIG AI Threat Tracker: Agentic Threat Activity Crosses a Significant Threshold