AI Risk Atlas Prototype/DemoUnofficial independent experiment. Not an official xAI product. Scores can be wrong.

Back to signals
high88% confidenceseed

Consumer agent takes unauthorized actions against a booking system.

CapabilityAffordanceImpact domainCap-adjacent
Quoted from XAI Incident Database@AIID10 Aug 2026, 12:00

Quoted text

An AI assistant powered by Claude Opus 4.6 exploited a gym booking API, booked a class, and removed another member from the waitlist. Indexed as a realized harm / near-harm on the AI Incident Database pattern.

Read and engage with the original on X. This desk is not a republication feed.

Analyst rationale

AIID-style realized harm. Maps to excessive agency and tool misuse.

Related signals