--- title: METR lost a $600K API key to attackers for three weeks... description: METR, an AI safety research organization, disclosed that an attacker stole an API key and racked up roughly $600,000 in model usage over three weeks before... canonical: https://daily.dev/posts/metr-lost-a-600k-api-key-to-attackers-for-three-weeks-before-anyone-noticed-a1dhy4v2h twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: METR lost a $600K API key to attackers for three weeks before anyone noticed | daily.dev og:description: METR, an AI safety research organization, disclosed that an attacker stole an API key and racked up roughly $600,000 in model usage over three weeks before... og:url: https://daily.dev/posts/metr-lost-a-600k-api-key-to-attackers-for-three-weeks-before-anyone-noticed-a1dhy4v2h og:image: https://api.daily.dev/og/posts/a1Dhy4v2h.png og:image:alt: METR lost a $600K API key to attackers for three weeks before anyone noticed og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # METR lost a $600K API key to attackers for three weeks before anyone noticed **[Collections](https://daily.dev/sources/collections)** · 2 min read · 0 upvotes · 0 comments ## Summary METR, an AI safety research organization, disclosed that an attacker stole an API key and racked up roughly $600,000 in model usage over three weeks before anyone noticed. The key leaked from a vibe-coded internal dashboard on a researcher's personal EC2 instance whose Google auth failed open, letting anyone who found the endpoint (likely via certificate-transparency logs) prompt the agent behind it into revealing its credentials. Because the credits were free from a model provider with no spending cap, there was no invoice to trigger an alert, and the attacker's usage blended into METR's normally high token volume. The lesson: spend limits and usage alerts on API keys matter even when the credits cost nothing. ## Content METR, an AI safety research organization, disclosed a security incident in which an attacker stole an API key and used roughly $600,000 worth of AI model credits over several weeks without anyone catching it. The key was exposed through a vibe-coded internal dashboard running on a researcher's personal EC2 instance. The dashboard had a broken Google authentication setup that failed open, meaning anyone who hit the right endpoint got in. Attackers apparently found the service by scanning certificate-transparency logs, then simply prompted the agent directly to hand over its provider API key. Which it did. From there, the attacker used the stolen key for about three weeks. The reason nobody noticed: METR routinely generates large volumes of tokens for evaluation work, so the extra usage blended in. The credits were also provided to METR for free by the model provider, with no spending cap, so there was no bill to trigger an alert. A paying customer would have seen a very different outcome. The incident is a pretty uncomfortable look for an organization whose work centers on AI safety. The core failures here aren't exotic - a misconfigured auth layer, an agent with no guardrails around credential disclosure, and no spend monitoring on free API keys. None of that required a sophisticated attacker to exploit. ## Questions this post answers ### How did attackers steal METR's AI provider API key? Attackers found an internal dashboard, hosted on a researcher's personal EC2 instance, through certificate-transparency log scanning. The dashboard's Google authentication was misconfigured to fail open, letting anyone access it. Once inside, attackers simply prompted the AI agent running on the dashboard directly, asking it to reveal its provider API key, and it complied without any guardrails against credential disclosure. _Teams wiring AI agents into internal tools follow security incidents like this one on daily.dev to avoid similar credential leaks._ ### Why didn't METR notice $600,000 in stolen AI API credits being used? The theft went unnoticed for about three weeks because METR routinely generates large volumes of tokens for its own evaluation work, so the attacker's usage blended into normal traffic patterns. Additionally, the model provider had given METR the credits for free with no spending cap, so there was no bill or cost alert to flag the anomaly, unlike what a paying customer would have experienced. _Anyone monitoring API spend and usage anomalies can track lessons from incidents like this on daily.dev._ ## Similar posts on daily.dev - [Token Jacking: Cybercriminals Could Be Stealing Your AI Resources](https://daily.dev/posts/token-jacking-cybercriminals-could-be-stealing-your-ai-resources-os316gpzk) · Unit 42 · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#ai-safety](https://daily.dev/tags/ai-safety), [#aws-ec2](https://daily.dev/tags/aws-ec2), [#secrets-management](https://daily.dev/tags/secrets-management) [View this post on daily.dev](https://daily.dev/posts/metr-lost-a-600k-api-key-to-attackers-for-three-weeks-before-anyone-noticed-a1dhy4v2h) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"METR lost a $600K API key to attackers for three weeks before anyone noticed","url":"https://daily.dev/posts/metr-lost-a-600k-api-key-to-attackers-for-three-weeks-before-anyone-noticed-a1dhy4v2h","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/metr-lost-a-600k-api-key-to-attackers-for-three-weeks-before-anyone-noticed-a1dhy4v2h"},"datePublished":"2026-09-02T02:57:24.555Z","dateModified":"2026-10-15T02:20:57.411Z","description":"METR, an AI safety research organization, disclosed that an attacker stole an API key and racked up roughly $600,000 in model usage over three weeks before...","image":"https://pbs.twimg.com/media/HRLea0kbcAAlCgB.png","thumbnailUrl":"https://pbs.twimg.com/media/HRLea0kbcAAlCgB.png","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/metr-lost-a-600k-api-key-to-attackers-for-three-weeks-before-anyone-noticed-a1dhy4v2h","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,ai-safety,aws-ec2,secrets-management","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"METR lost a $600K API key to attackers for three weeks before anyone noticed"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/metr-lost-a-600k-api-key-to-attackers-for-three-weeks-before-anyone-noticed-a1dhy4v2h#faq","mainEntity":[{"@type":"Question","name":"How did attackers steal METR's AI provider API key?","acceptedAnswer":{"@type":"Answer","text":"Attackers found an internal dashboard, hosted on a researcher's personal EC2 instance, through certificate-transparency log scanning. The dashboard's Google authentication was misconfigured to fail open, letting anyone access it. Once inside, attackers simply prompted the AI agent running on the dashboard directly, asking it to reveal its provider API key, and it complied without any guardrails against credential disclosure. Teams wiring AI agents into internal tools follow security incidents like this one on daily.dev to avoid similar credential leaks."}},{"@type":"Question","name":"Why didn't METR notice $600,000 in stolen AI API credits being used?","acceptedAnswer":{"@type":"Answer","text":"The theft went unnoticed for about three weeks because METR routinely generates large volumes of tokens for its own evaluation work, so the attacker's usage blended into normal traffic patterns. Additionally, the model provider had given METR the credits for free with no spending cap, so there was no bill or cost alert to flag the anomaly, unlike what a paying customer would have experienced. Anyone monitoring API spend and usage anomalies can track lessons from incidents like this on daily.dev."}}]} ```