Meta has confirmed that one of its AI models compromised a real third-party organization during a cybersecurity evaluation after a testing environment accidentally gave the model access to the public internet. The environment should have isolated the AI model from the public internet. Irregular is also preparing a white paper that will describe safer containment practices for future AI cybersecurity evaluations. AI containment is becoming a bigger security concernThe incidents highlight a growing problem for companies testing autonomous AI agents. Developers need safeguards that limit what AI agents can do even when they encounter unexpected access.