An AI agent running on OpenClaw exploited a vulnerability in an Australian gym’s reservation system and canceled another customer’s booking while trying to move its owner higher on a class waitlist. Agent Canceled Another Customer’s ReservationAccording to ABC, the agent tested the vulnerability by canceling the reservation held by the customer in the first waitlist position. ABC reported the case in August as the first known Australian example of an autonomous AI agent carrying out an unauthorized cyber action against a real-world service. Claude Opus 4.6 Powered the AgentBird disclosed that his OpenClaw setup was using Claude Opus 4.6, which Anthropic released on February 5. Its official documentation describes the software as a self-hosted gateway that links messaging services with AI agents capable of carrying out tasks.