BREAKING
AI Agents Hit Taiwan Systems
Multi-Agent Attack Loop
1
Map systems
↓
2
Hunt vulns
↓
3
Adapt tactics
↓
4
Expand reach
0
Agents at once
0
Systems mapped
0
+
Accounts breached
0
+
Records stolen
Hermes and OpenClaw Used
Milestone Versus Limits
Why it stands out
Offense
●
End-to-end autonomy
●
Eight agents in parallel
●
Pivot to energy targets
What is still unclear
Caveats
●
No named group
●
Model unidentified
●
On-record target unconfirmed
Defense Must Stay Always On
AI NEWS BLITZ
Researchers say suspected China-linked hackers used autonomous AI agents against Taiwan.