A vibe-coded app exposed METR's API key and consumed $600,000 in free credits

The AI evaluator says a March breach exposed an API key, while a May campaign probed an endpoint that could theoretically expose sensitive model outputs. METR believes attackers did not access that data.

By · Published

Primary source: METR

Why it matters

Independent AI evaluators need privileged model access to remain useful. METR's near-misses show that ordinary deployment shortcuts can threaten the trust supporting that access.

A miniature model of a data center complex under bright daylight, with a glowing digital key floating above server racks and scattered abstract credit tokens.

Elizabeth "Beth" Barnes (@bethmaybarnes), the founder and CEO of METR, disclosed in an August 31st security update that external attackers exploited weaknesses around the AI evaluator's public infrastructure in two incidents earlier this year. One stolen API key was used to consume model credits with a list value of approximately $600,000.…

Reader comments

Conversation for this story loads after sign-in.