An Attacker Built a Credential-Harvesting Pipeline With a Multi-Agent Framework in Under Six Hours

Google Cloud Threat Intelligence·high signalXBlueskyLinkedInCopy link

Google Threat Intelligence Group's Q3 2026 AI Threat Tracker documents a financially motivated actor who compromised cloud infrastructure and combined a coding chatbot, a prompt and predefined agent instructions into an autonomous vulnerability-scanning and credential-harvesting pipeline in less than six hours. The resulting production dashboard organized and validated more than 23,800 harvested secrets, including cloud and AI service credentials. GTIG also found an exposed C2 server running an agentic recon platform whose directories contained AGENTS.md, KNOWLEDGE.md and .openclaw/ components, meaning attackers are now shipping the same agent-harness conventions builders use.