Google GTIG AI Threat Tracker: Google says it found threat actors using LLM frameworks to fully automate vulnerability discovery and exploitation without a human in the loop for the first time
Google Threat Intelligence Group (GTIG) and Mandiant say in their AI Threat Tracker update that multiple threat actors are abusing open source agentic penetration-testing frameworks, naming ARTEX, CAIRN, CyberStrikeAI and PentAGI, to automate parts of live intrusions; GTIG says it observed CAIRN used in intrusion activity against targets including in the US aerospace sector.
GTIG says that in the past quarter it identified threat actors using LLM frameworks to fully automate vulnerability discovery and exploitation without a human in the loop for the first time: it found an exposed staging server hosting a multi-agent vulnerability research and weaponization framework, dubbed exploit_agent, that integrates with multiple frontier and local LLMs, and victim telemetry on the server suggests the operator targeted French websites in the media and entertainment industries and the education sector.
In a section on North Korean (DPRK) actors, GTIG says a suspected MIDNIGHT NEPTUNE threat cluster modified .claude/settings.json files in internal code repositories so that starting Claude Code triggered the download of the SOMBERMEME backdoor. GTIG also cites the August 2026 PaperCut zero-days (CVE-2026-81578 and CVE-2026-82078) as an example, saying Greynoise reported a campaign in which a threat actor likely used LLMs to build and test exploits. (source: Google Cloud blog)
BleepingComputer reported on the GTIG findings on 16 November 2026. (source: BleepingComputer)
- Product
- Agentic AI / LLM frameworks abused for intrusions (ARTEX, CAIRN, CyberStrikeAI, PentAGI, exploit_agent)
