CyberSecurity News
AI Model Evaluator METR Hit by Credential Theft, Probing
Dark Reading
· September 1, 2026AI summary
Threat actors carried out an attack on the AI Model Evaluator METR, resulting in the theft of an API key. This stolen key was then used to consume a substantial amount of public AI model credits, totaling $600,000, belonging to the security nonprofit organization.
This is an AI-generated brief aggregated by HackerFeeds for convenience and grounded in the source’s own summary; the related CVE, threat-group and country data is from HackerFeeds’ own indexes. The original article is the authoritative source — all rights belong to Dark Reading.