Attacker stole a METR API key, used $600K worth of credits, and no one noticed for weeks
Attackers stole a METR API key via an exposed agent-run EC2 instance and consumed about $600,000 in public model credits over three weeks.
AI evaluation nonprofit METR disclosed two incidents. In March 2026, a fail-open bug in a vibe-coded app disabled authentication on a publicly accessible EC2 instance; an attacker prompted the running agent to reveal a model provider API key, added an SSH key for persistence, and consumed roughly $600,000 in free public-model credits over three weeks without being noticed. In May 2026, attackers probed METR's public infrastructure using agents, automated vulnerability discovery, credential stuffing, OAuth token attempts, and phishing; a separately exposed read-only SQL mechanism found by a bug bounty hunter risked leaking unpublished evaluation data, but no access to non-public data was confirmed.
- Fail-open auth bug exposed an EC2 instance running agents for several days
- Attacker used the agent to reveal an API key, added SSH persistence, spent $600K in credits
- High routine usage and free credits masked the abnormal consumption for weeks
- May campaign included credential stuffing, OAuth grant attempts, and new-service scanning
- METR paid a bug bounty, isolated production systems, and hired a security lead
- Tags
- agent-securityai-infrastructureapi-key-theftaws-ec2cloud-securitycredential-theftincident-responsemetr
- Vendors
- Amazon Web ServicesGoogle
- Products
- Amazon EC2
- Victims
- METR
- Organizations
- METROpenAIHugging Face
From the original article
3 min read at theregister.comThe model provider gave METR the credits for free. An actual customer would not have been so lucky
By Jessica Lyons · theregister.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.