Attackers Drain $600,000 in AI Credits After Stealing METR API Key
The AI safety non-profit says intruders got into a staff laptop and a code repository, but no sensitive research data was taken.
Key points
- METR, a US non-profit that tests advanced AI models, disclosed two break-ins where outsiders got into its systems.
- Attackers stole an API key, a kind of digital password used by software, and burned through roughly $600,000 of AI credits.
- A second intrusion involved unauthorised access to a private code repository belonging to the organisation.
- METR says no sensitive research data or model evaluation results were taken in either incident.
- The non-profit is rotating credentials and tightening internal access controls in response.
METR, the Model Evaluation and Threat Research group, has disclosed that attackers hit its systems twice this year. The organisation tests frontier AI models to see whether they can carry out long, complex tasks on their own.
In the first incident, criminals got hold of an API key belonging to METR. An API key is essentially a password that lets one piece of software talk to another. Whoever held it could spend money on AI services on METR's tab.
They spent a lot. Around $600,000 in AI credits were consumed before the theft was caught, according to a disclosure first reported by The Hacker News.
The second incident was separate. Attackers gained access to a private source code repository, the internal store where METR's software is written and kept. The non-profit says no sensitive information was taken.
Who is METR and why would anyone target them?
METR is a small research non-profit that stress-tests the world's most powerful AI models. Its work sits close to the labs building those systems and to governments trying to write rules for them. That makes both its research and its cloud accounts attractive targets.
Pronounced "Meter", the group is best known for measuring how long a task an AI system can carry out unsupervised, a benchmark policymakers now cite when discussing AI risk. This is the third API-key-theft incident we've reported since June, when we first covered credential abuse of this kind.
How did the attackers get in?
METR says the first intrusion started with a compromised staff laptop. From that machine, the attackers pulled an API key stored locally, then used it to run up a bill on AI services.
How the code repository was accessed in the second incident hasn't been publicly detailed, other than that it involved an outside party. No customer data is involved, because METR doesn't run a consumer product.
What was actually taken?
Money, in effect. Not research.
| Incident | What attackers reached | Impact |
|---|---|---|
| First | A METR API key on a staff device | About $600,000 in AI credits spent |
| Second | A private source code repository | No sensitive data taken, per METR |
METR says its model evaluation results, unpublished research and information shared under agreement with AI labs were not exposed.
Should ordinary people be worried?
No, not directly. METR doesn't hold payment details or personal records for members of the public. The damage was financial and reputational, borne by the non-profit and the AI vendor whose credits were drained.
The wider point matters more. API keys are the quiet plumbing of modern software, and when one leaks from a developer's laptop the bill can climb into six figures within hours. Companies using AI services should treat those keys with the same care as bank credentials.
What is METR doing now?
The non-profit is rotating affected credentials, reviewing how secrets are stored on staff devices, and tightening who can reach internal repositories. It has also said it will share more technical detail as its investigation continues.
For a research group whose job is to warn the world about capable AI systems being misused, being on the receiving end of a straightforward credential theft is an awkward moment. It's also a common one.
