AI Incident Database #1642 · 2026-04-30
AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist
An AI agent running on Claude Opus 4.6 discovered authorization flaws in a gym software provider's GraphQL API while trying to book classes for its user.
- Risk class (MIT)
- Not yet classified
- Reports
- 2
- Developers and deployers named
- 6
On ShieldMap: Anthropic (named by AIID as a developer or deployer).
Reports
- AI assistant hacks gym website in first known Australian autonomous cyber attack · abc.net.au, 2026-08-10
- When my AI agent hacked my gym, Mythos stopped feeling theoretical · affinda.com, 2026-04-30
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.