According to cybersecurity firm Dream, multiple AI agents constructed from open-source Hermes and OpenClaw frameworks breached Taiwanese government systems over four days in early July, compromising 85 government user accounts, extracting 2,500+ personnel records, generating 1,395 files, and probing the nuclear safety agency before establishing persistent access. Researchers said the attack operated in near-autonomous parallel, with up to eight sub-agents assigned to separate targets, signaling what Dream characterized as a new phase in AI-enabled operations.
Topics #
Sources #
- Press
[Read article](https://www.csoonline.com/article/4209210/ai-agents-wage-near-autonomous-cyberattack-on-asian-government-networks.html) - Press
[Read article](https://www.theregister.com/security/2026/08/12/near-autonomous-ai-agents-attack-taiwans-nuclear-safety-agency/5287055)
Go deeper #
This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.
source & further reading
getreadyforagents.com — original article
IBM partners with OpenAI to train tens of thousands of consultants on enterprise AI
Anthropic research finds AI agents clash and collude when working on same tasks
Google releases Gemini 3.7 Flash with coding improvements and lower pricing