UNC6993
Threat actorRecent news
Attackers hijack corporate AI model access, running up cloud bills of up to $1 million
Google Threat Intelligence Group and Mandiant describe LLMJacking, where attackers abuse stolen cloud credentials, GitHub tokens and session tokens to run unauthorised calls against corporate large language models. In one incident, over 500,000 API calls were made in under eight hours through a token-routing service called Jet Night, costing one organisation nearly $1 million. Attackers also used tiny test requests to avoid triggering alerts and created admin accounts and backdoors, so monitoring for billing spikes alone is not enough.
Stolen enterprise AI model access resold via LLM Mixers, with victim cloud bills reaching $1 million
Google Threat Intelligence Group reports LLMjacking campaigns in which attackers steal cloud identity tokens and LLM API keys, then route requests through criminal gateways called LLM Mixers that resell access. Fake charges can exceed $100,000 a day, and some cumulative bills reached $1 million before keys were revoked. Attackers often test keys with single-token requests first, so low-volume activity can slip under spend-based alerts.