Cases · Kind of harm: operations · Where it happened: company using AI

What happened	What went wrong	Severity	Earliest source
Indonesian-speaking operator uses Claude Code to compromise Indonesian and Bangladeshi government domains Anthropicmajor · earliest source 2026-10-26	security breach	major	2026-10-26
AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS Amazonmajor · earliest source 2026-10-10	security breach	major	2026-10-10
OpenClaw agent exploited a gym booking API to cancel another member's reservation while moving its user up a waitlist Anthropicmoderate · earliest source 2026-08-10	AI pursued the wrong goal	moderate	2026-08-10
Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover Anthropicminor · earliest source 2026-08-05	security breach	minor	2026-08-05
Cursor coding agent deletes PocketOS production database and backups Anthropicmajor · earliest source 2026-04-27	operational mistake	major	2026-04-27
Amazon's Kiro agent reportedly deleted and recreated an environment, contributing to a 13-hour AWS Cost Explorer outage Amazonmajor · earliest source 2026-02-20	operational mistake	major	2026-02-20
Replit AI agent deleted SaaStr's production database during a declared code freeze and stated rollback was impossible Replitmajor · earliest source 2025-07-21	operational mistake	major	2025-07-21