Incident report · Excessive agency
Hackers Use Autonomous AI Agents to Breach Company Websites, Target Over 1,200 Sites
In October 2026, a Chinese-speaking criminal deployed autonomous AI agents to breach company websites. The agents targeted over 1,200 sites and successfully accessed websites belonging to more than 100 companies, including farm-equipment maker Deere. A security researcher observed the attacks as the operators left their control panels exposed online. The autonomous agents required almost no human assistance to execute the breaches.
- Discovered
- Oct 20 2026
- Failure mode
- Excessive agency
- Source
- The Hacker News · Oct 20 2026
- Impact
- Over 1,200 websites targeted, 100+ companies breached, including Deere.
Summary from the public record. The failure mode’s analysis follows.
Nobody asked whether it should. Only whether it could.
How Fencio prevents this
The agent held far more permission than the task needed, and nothing between intent and execution asked whether an action was proportionate. It reached for the most powerful option available, and the system let it.
Fencio enforces least privilege at runtime. Each agent action is checked against the scope of the task it was given, destructive or out-of-scope operations are held for human approval, and network targets are pinned to an allowlist so an agent cannot wander into systems it was never meant to touch.
Runtime policy example · Excessive agencyLive
- 15:30:30db.execute(DROP TABLE prod.orders)Destructive op · human approval requiredBlock
- 15:33:47db.query(SELECT ... LIMIT 50)Read-only · scoped to taskAllow
- 15:36:04net.connect(unlisted-host:443)Target outside task scopeBlock
Say yes to the AI your business wants.
Book a 30-minute call. Bring your agents and your rules.