Attackers Steal METR API Key and Consume AI Credits Worth About $600,000
- ID
- 20174
- Status
- summarized
- Published
- 01 Sep 2026, 5:05 PM
- Fetched
- 01 Sep 2026, 6:35 PM
- Provider
- The Hacker News
- Category
- security
- Original URL
- https://thehackernews.com/2026/09/attackers-steal-metr-api-key-and.html
- Source URL
- https://feeds.feedburner.com/TheHackersNews
Summary
- Score
- 8.5
- Created
- 01 Sep 2026, 6:35 PM
- Tags
- Audience
- developersvibe_codersai_agent_usersai_ml_learners
What happened
METR, a non-profit that evaluates frontier AI models for agentic tasks, disclosed two security incidents. In March 2026, attackers found a researcher's personal EC2 instance running a 'vibe-coded' agent orchestration dashboard via certificate transparency logs, exploited a fail-open auth vulnerability that silently disabled Google authentication, then prompted the agent directly to reveal its model provider API key—consuming approximately $600,000 in AI inference credits over three weeks. In May 2026, attackers separately probed METR's public infrastructure but failed to access internal data.
Why it matters
If you are vibe-coding or rapidly prototyping agent dashboards with LLM API keys, you need to assume attackers are actively scanning certificate transparency logs for sites with LLM/agent keywords and will prompt your exposed agent to dump its API key. Rotate and restrict API keys, never rely solely on Google auth without a fail-closed fallback, and set spending alerts on any inference account. The $600,000 bill was only absorbed because the provider gave credits for free—you would not be so lucky.
Discussion angle
The attacker didn't exploit a complex vulnerability—they simply asked the agent to reveal its API key. This is a new class of social-engineering attack surface that anyone shipping agent orchestration tools needs to design against: agents that can access and output their own credentials are a liability, not just a feature.