AI Agent · OpenAI · Taiwan · China · Israel · The Register
'Near-autonomous' AI agents attack Taiwan's nuclear safety agency
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Some say the world will end in fire, some say an agentic swarm.
Key facts
- According to Dream, the attack framework, built on open source Hermes and OpenClaw AI agents, deployed up to eight sub-agents, each assigned to its own targets and attack techniques, across 12
- Over the first four days of July, AI agents compromised 85 government user accounts and extracted more than 2,500 personnel records, according to Dream, an Israeli cybersecurity firm
- Using employee usernames harvested from an unauthenticated API, the agents broke into a government department’s office automation portal, solving its CAPTCHAs with 100 percent accuracy
- OpenAI technical staffer Michael Dalton, in a Black Hat briefing last week about the Hugging Face attack, said “AI orchestrated, fully automated offensive attacks are real now
Summary
Suspected Chinese cyber operatives used publicly available AI tools to compromise Taiwanese government systems before expanding the attack to its nuclear safety agency, supply-chain vendors, and at least seven energy companies in what security researchers called a "near-autonomous attack. Over the first four days of July, AI agents compromised 85 government user accounts and extracted more than 2,500 personnel records, according to Dream, an Israeli cybersecurity firm. Dream, in research published on Wednesday, detailed the intrusions and said that the suspected Chinese hackers hit “government entities in Asia” - but declined to say which government had been attacked. A person familiar with the attack confirmed to The Register that Taiwan was the target.