Google Warns of LLMJacking Attacks Generating Over $100,000 Daily
Original title: Google Warns of LLMJacking Attacks That Generate Over $100,000 in Cloud AI Bills Per Day
Attackers hijack enterprise LLM access to run up massive fraudulent charges before access is revoked.
Google’s Mandiant reported attackers hijacking enterprise access to large language models, running up fraudulent cloud charges exceeding $100,000 in a single day. Victims include financial services, retail, technology, and transportation. Actors use stolen IAM credentials and abuse vulnerabilities in gateways like LiteLLM. Google recommends least privilege access and key rotation.
- Over $100,000 in fraudulent charges in one day at some organizations
- Attackers create rogue IAM accounts and pull secrets
- LiteLLM /key/regenerate endpoint exploited (CVE-2026-40217)
- AI API keys harvested from public GitHub repositories
Impact: unauthorized use of cloud AI services for fraudulent billing
- 1.implement centralized secrets management with automatic rotation
- 2.set API quotas and budget alerts
- 3.use phishing-resistant MFA
- CVEs
- CVE-2026-40217
- Vendors
- Products
- Gemini APIBedrock
- Threat actors
- UNC6993
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2026-40217 | LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI | 8.8 | 16% | PoC |
From the original article
2 min read at gbhackers.com
Google’s Mandiant and Threat Intelligence Group (GTIG) say attackers are hijacking enterprise access to large language models and running up huge fraudulent cloud charges. Google’s report documents more than $100,000 in a single day. At some organizations, cumulative charges reached $1 million before they revoked access.
By Divya · gbhackers.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.