Autonomous AI Agents Exploit Credentials in Six-Hour Cyberattack Campaign

Autonomous AI agents executed a large-scale credential harvesting campaign, compromising thousands of credentials in under six hours. The attack involved AI-driven techniques like prompt injection and AI model exploitation, highlighting growing threats to enterprise AI assets and supply chains.

Threat actors are continuing to leverage artificial intelligence (AI) to streamline their operations, with one financially motivated hacking group employing an autonomous, multi-agent attack framework to carry out a large-scale credential harvesting campaign within six hours.

Google Threat Intelligence Group (GTIG) said it has observed attackers with diverse motivations targeting proprietary AI

Read original article