AI Model Evaluator METR Hit by Credential Theft, Probing

Summary

The AI model evaluation nonprofit METR has been targeted by threat actors who successfully stole an API key. This credential theft allowed the attackers to access and use METR's public AI model credits, resulting in a loss of approximately $600,000. The incident highlights the risks associated with API key management and the potential financial impact of credential compromise.

Indicators of Compromise

• malware — credential theft

Entities