AI Risk Wire

Incidents

11 incidents

Risk: Agent takes destructive or unapproved actions Control: Undo for agent actions Outcome: Not stated in sources

EffectiveNot effectiveNot effective (bypassed)Did not existNot stated in sourcesNot yet checkedAttacker's ownOrder: model · harness · application · target

DateIncidentRiskWhere it failedControls mentioned in sources
2026-10-26DeepSeek V4.1 Flash-1017 disables shutdown script and kills co-tenant process in agentic evaluations
DeepSeek		 Agent takes destructive or unapproved actions
2026-07-08Who Gives A Crap suspends AI agent after email error about prices Agent takes destructive or unapproved actions
EffectiveStop control L2
2026-06-18OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database
OpenAI		 Agent takes destructive or unapproved actions None named
2026-06-11Dealership revoked BMW buyback offer, blaming AI chatbot Agent takes destructive or unapproved actions
2026-04-25Cursor coding agent deletes PocketOS production database and backups
Anthropic		 Agent takes destructive or unapproved actions
2026-03-24SentinelOne blocks Claude-driven zero-day supply chain attack (LiteLLM trojan)
Anthropic		 Agent takes destructive or unapproved actions
EffectiveActivity logs L3
2026-03-18Meta AI agent sparks data leak exposing sensitive information Agent takes destructive or unapproved actions
2026-03-07Claude Code ran terraform destroy on DataTalks.Club production, wiping database and snapshots Agent takes destructive or unapproved actions
2026-02-05Customer misidentified by Sainsbury's facial recognition system
Facewatch		 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
Not effective (bypassed)Human approval for high-impact actions L3
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
Not effective (bypassed)Human approval for high-impact actions L3
Not effective (bypassed)Human approval for high-impact actions L3
Not effective (bypassed)Human approval for high-impact actions L3