Wire · technology
AI safety organization METR reports API key theft and credit misuse
◆ Sectors
◆ Source
◆ Verified
Fusion42 · 3 September 2026 · Fusion42 review
AI safety group METR suffered a security breach where an API key was stolen and used to rack up $600,000 in model credits. The group also faced automated attacks probing for vulnerabilities, leading to credential revocation and improved security controls.
This Wire brief sits within Fusion42's coverage of AI & ML, and 2 sources have reported it between 2 Sep 2026 and 3 Sep 2026.
◆ ◆ The Wire takeaway
Your AI model deployment is now a target for hidden abuse that can silently drain credits. Lock down API keys and impose spending limits this week to avoid costly surprises.
◆ Coverage
2 sources · first reported 2 Sep 2026 · latest 3 Sep 2026
◆ Related on Wire
◆ Topics