One runaway AI agent racked up a $50,000 cloud bill

Mandiant’s testing found prompt injection remains a primary attack vector in enterprise AI deployments, alongside weak file permissions and poor access controls. The report also highlighted an AI agent that generated a large cloud bill during testing, showing how agentic systems can create direct financial risk.

According to Mandiant’s testing, prompt injection remains a primary attack vector in enterprise AI deployments, and one AI agent during testing was able to autonomously generate a roughly $50,000 cloud bill, demonstrating that agentic systems can directly trigger significant financial impact when insufficiently constrained. The report also notes contributing weaknesses such as poor file permissions and access controls, which increase the blast radius of misbehaving or compromised agents. From RealGround’s perspective, this illustrates the need for robust guardrails on AI agents, strict budget and resource limits, and secure business logic design to prevent uncontrolled actions. Continuous adversarial testing of agent behavior and hardening of permissions can substantially reduce both security and financial risk from AI agent abuse.