--- title: Google: LLMjacking attacks rack up $1 million in cloud... description: LLMjacking attacks are generating large fraudulent cloud AI bills, with some organizations losing over $100,000 a day and cumulative charges reaching $1... canonical: https://daily.dev/posts/google-llmjacking-attacks-rack-up-1-million-in-cloud-ai-charges-cvokzb9hu twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Google: LLMjacking attacks rack up $1 million in cloud AI charges | daily.dev og:description: LLMjacking attacks are generating large fraudulent cloud AI bills, with some organizations losing over $100,000 a day and cumulative charges reaching $1... og:url: https://daily.dev/posts/google-llmjacking-attacks-rack-up-1-million-in-cloud-ai-charges-cvokzb9hu og:image: https://api.daily.dev/og/posts/cVOKZB9hU.png og:image:alt: Google: LLMjacking attacks rack up $1 million in cloud AI charges 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. # Google: LLMjacking attacks rack up $1 million in cloud AI charges **[BleepingComputer](https://daily.dev/sources/bleepingcomputer)** · 4 min read · 0 upvotes · 0 comments ## Summary LLMjacking attacks are generating large fraudulent cloud AI bills, with some organizations losing over $100,000 a day and cumulative charges reaching $1 million. Google's Threat Intelligence Group and Mandiant found two operational clusters: one scanning for exposed LLM endpoints, another stealing API keys from unprotected machines. Stolen access gets resold through 'LLM mixer' services like Jet Night, which sells 'unlimited access plans' for $60 a month. One threat actor executed more than 500,000 API calls in under eight hours, and Jet Night passed nearly $1 million in token costs to the victim. Attackers also exploited CVE-2026-40217, a flaw in LiteLLM that allows running arbitrary code on the server via its guardrail testing endpoint. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is LLMjacking and how do attackers make money from it? LLMjacking is the theft and resale of access to cloud-hosted LLM services using stolen API keys or compromised credentials. Attackers sell this access to 'LLM mixer' services, such as Jet Night, which charge subscribers as little as $60 a month for unlimited access while routing requests through victims' hijacked accounts, generating fraudulent charges of over $100,000 per day in some cases. _Teams managing LLM API spend can track emerging attack patterns like this on daily.dev._ ### What is CVE-2026-40217 in LiteLLM? CVE-2026-40217 is a vulnerability in LiteLLM that allows an attacker to run arbitrary code on the server by abusing the custom-code guardrail testing endpoint. Google's Threat Intelligence Group and Mandiant observed threat actors exploiting this flaw as part of broader LLMjacking campaigns to gain unauthorized access to enterprise LLM infrastructure. _Anyone running LiteLLM in production can follow disclosures like this one on daily.dev before patching decisions get urgent._ ### How can organizations detect or prevent LLMjacking attacks on their cloud LLM infrastructure? Google recommends prioritizing identity and access management, using centralized secrets platforms for key rotation, denying all permissions not explicitly required including access to cloud LLM services, enforcing phishing-resistant MFA, setting API usage and spending limits, and monitoring cloud audit and inference logs for unauthorized service activation or unusual usage patterns. _Cloud security teams hardening LLM access policies can keep up with guidance like this via daily.dev._ ## Similar posts on daily.dev - [LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools](https://daily.dev/posts/llmjacking-evolved-attackers-are-using-stolen-ai-compute-to-build-offensive-agentic-tools-klku1uvkk) · Sysdig Blog · 1 upvotes · 0 comments - [LiteLLM flaws let low-privileged users hijack AI gateway and steal provider keys](https://daily.dev/posts/litellm-flaws-let-low-privileged-users-hijack-ai-gateway-and-steal-provider-keys-z1eue9ebf) · IT Security Guru · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#gcp](https://daily.dev/tags/gcp), [#litellm](https://daily.dev/tags/litellm) [View this post on daily.dev](https://daily.dev/posts/google-llmjacking-attacks-rack-up-1-million-in-cloud-ai-charges-cvokzb9hu) ```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":"Google: LLMjacking attacks rack up $1 million in cloud AI charges","url":"https://daily.dev/posts/google-llmjacking-attacks-rack-up-1-million-in-cloud-ai-charges-cvokzb9hu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/google-llmjacking-attacks-rack-up-1-million-in-cloud-ai-charges-cvokzb9hu"},"datePublished":"2026-11-03T18:54:52.409Z","dateModified":"2026-11-03T19:19:22.937Z","description":"LLMjacking attacks are generating large fraudulent cloud AI bills, with some organizations losing over $100,000 a day and cumulative charges reaching $1...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0fe1d5257bcc2f09010b3de91977abce?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0fe1d5257bcc2f09010b3de91977abce?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"BleepingComputer","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":"BleepingComputer","logo":"https://media.daily.dev/image/upload/s--as8nJ3qy--/f_auto,q_auto/v1774959951/logos/bleepingcomputer?_a=BAMAMiWQ0","url":"https://daily.dev/sources/bleepingcomputer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/google-llmjacking-attacks-rack-up-1-million-in-cloud-ai-charges-cvokzb9hu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,gcp,litellm","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"BleepingComputer","item":"https://daily.dev/sources/bleepingcomputer"},{"@type":"ListItem","position":3,"name":"Google: LLMjacking attacks rack up $1 million in cloud AI charges"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/google-llmjacking-attacks-rack-up-1-million-in-cloud-ai-charges-cvokzb9hu#faq","mainEntity":[{"@type":"Question","name":"What is LLMjacking and how do attackers make money from it?","acceptedAnswer":{"@type":"Answer","text":"LLMjacking is the theft and resale of access to cloud-hosted LLM services using stolen API keys or compromised credentials. Attackers sell this access to 'LLM mixer' services, such as Jet Night, which charge subscribers as little as $60 a month for unlimited access while routing requests through victims' hijacked accounts, generating fraudulent charges of over $100,000 per day in some cases. Teams managing LLM API spend can track emerging attack patterns like this on daily.dev."}},{"@type":"Question","name":"What is CVE-2026-40217 in LiteLLM?","acceptedAnswer":{"@type":"Answer","text":"CVE-2026-40217 is a vulnerability in LiteLLM that allows an attacker to run arbitrary code on the server by abusing the custom-code guardrail testing endpoint. Google's Threat Intelligence Group and Mandiant observed threat actors exploiting this flaw as part of broader LLMjacking campaigns to gain unauthorized access to enterprise LLM infrastructure. Anyone running LiteLLM in production can follow disclosures like this one on daily.dev before patching decisions get urgent."}},{"@type":"Question","name":"How can organizations detect or prevent LLMjacking attacks on their cloud LLM infrastructure?","acceptedAnswer":{"@type":"Answer","text":"Google recommends prioritizing identity and access management, using centralized secrets platforms for key rotation, denying all permissions not explicitly required including access to cloud LLM services, enforcing phishing-resistant MFA, setting API usage and spending limits, and monitoring cloud audit and inference logs for unauthorized service activation or unusual usage patterns. Cloud security teams hardening LLM access policies can keep up with guidance like this via daily.dev."}}]} ```