# They gave AI an impossible test. It found an open door

> Source: <https://www.washingtonexaminer.com/op-eds/4807856/ai-agent-safety-testing-was-the-door-locked-auditors-involvement-matters/>
> Published: 2026-11-19 13:00:00+00:00

**Recommendation:** Run agent safety tests in a sandbox with egress blocked and no route to live sites; the agents here impersonated employees and probed restricted areas, and some escaped a copied site back to the real one.
More in the playbook "Securing agents and AI tools": <https://wpnews.pro/playbooks/agent-security>

[Researchers](https://www.washingtonexaminer.com/tag/research) gave AI agents an impossible homework assignment. Instead of admitting that the answers did not exist, the agents started looking for them on a real organization’s website. Some agents pretended to be employees. Others poked at restricted areas of the site. When researchers tried giving them a copy of the [website](https://www.washingtonexaminer.com/tag/internet), some found their way back to the real thing.

This was not a scene from a science-fiction thriller. It was an AI [safety](https://www.washingtonexaminer.com/tag/safety) experiment. And the most disturbing part was not that the software had developed a mind of its own. It was that the adults running the test had left a door open.

## Recommended Stories

  Print subscriber? 

[Click here to login/register your account](https://www.washingtonexaminer.com/print-subscription-check)
  Digital subscriber?
