Multi

Gbhackers •Divya • August 25, 2026

A multi-agent AI framework, utilizing Hermes and OpenClaw agents, was employed to compromise government entities in Asia, stealing thousands of personnel records, cracking employee credentials, and establishing persistent access to state infrastructure, according to Dream Research Labs. Researchers discovered a 160 MB operational archive containing 1,395 files generated over 4 days of activity, from […]

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

AI Framework Breaches Government Systems in Asia, Stealing Thousands of Records A multi-agent AI framework, including Hermes and OpenClaw agents, was used to compromise government systems in Asia, resulting in the theft of over 2,500 personnel records and the cracking of 85 employee accounts. Dream Research Labs reported that the attack demonstrated the capability of coordinated AI agents to execute intrusion operations at machine speed. The operational archive discovered contained 1,395 files generated over four days of activity, highlighting the extensive nature of the breach. The attack showcases a significant shift in cyber capabilities, leveraging open-source AI tools for sophisticated intrusions. The current status of the breach is under investigation, with researchers analyzing the extent of the impact on affected government entities. 3 sources 68

Extracted Entities

Multi

The full story

Extracted Entities

Attack Types (1)

CWE Weaknesses (1)

Industries (1)

Malware (1)

Platforms (1)