CYBERSECURITYTRACKER
TRACKING6,506 stories in this site build1,309 vulnerability news stories in this site build
Permanent story citation

AI Model Evaluator METR Hit by Credential Theft, Probing

This page keeps the story as Cybersecurity Tracker first published it. If the tracker later corrects it, the correction appears below the original and never replaces it.

Back to newsStory 5506

As cited

Copy frozen at (site build).

breaches incidents

AI Model Evaluator METR Hit by Credential Theft, Probing

Threat actors stole an application programming interface (API) key from METR, a security nonprofit that evaluates artificial intelligence (AI) models, resulting in unauthorized consumption of $600,000 in public AI model credits. The incident is under investigation.

Why it matters: Security teams must monitor for API key exposure in development environments and third-party services, as compromised credentials can enable attackers to hijack cloud resources and incur substantial financial losses.

Source published
First seen by Cybersecurity Tracker

Source attribution

Glossary