LLMjacking: An Attack Method for Stealing Cloud Credentials

Summary:

A recent attack, termed LLMjacking, has emerged, utilizing stolen cloud credentials to target cloud-hosted large language model (LLM) services. These credentials were acquired from a widely targeted system running a vulnerable version of Laravel (CVE-2021-3129).

Threat Level – Red | Attack Report

To receive real-time threat advisories, please follow HiveForce Labs on LinkedIn.