AI Risk Wire

Incidents

8 incidents

Control: Human approval for high-impact actions Outcome: Did not hold

HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target

DateIncidentRiskChainControls named
2026-09-29Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer
Meta		 Privacy harm to a person
2026-08-05Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
Anthropic		 Hidden instructions hijack the agent
2026-08-05Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
OpenAI		 Hidden instructions hijack the agent
2026-07-23AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent
OpenAI		 Hidden instructions hijack the agent
2026-06-09Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address
Google		 Hidden instructions hijack the agent
2026-04-25Cursor coding agent deletes PocketOS production database and backups
Anthropic		 Agent takes destructive or unapproved actions
2025-12-01Amazon's Kiro agent reportedly deleted and recreated an environment, contributing to a 13-hour AWS Cost Explorer outage
Amazon		 Agent takes destructive or unapproved actions
2025-07-18Replit AI agent deleted SaaStr's production database during a declared code freeze and stated rollback was impossible
Replit		 Agent takes destructive or unapproved actions