4 min read
News Brief Kaspersky describes attackers using the open-source CyberStrikeAI framework, where a server-side LLM plans post-exploitation. Victims included education organizations.
Kaspersky describes attackers using the open-source CyberStrikeAI framework, where a server-side LLM plans post-exploitation. Victims included education organizations.
An attacker deployed Nous Research's open-source Hermes AI agent in YOLO mode against Thailand's Ministry of Finance, autonomously running reconnaissance, privilege escalation, and database exploitation with no operator in the loop.
Sysdig documented an LLM agent autonomously driving lateral movement from a marimo RCE to a PostgreSQL dump across four pivots in under two minutes. What this means for detection.