Sev0AI security incidents, tracked

All incidents / Meta

Meta AI security incidents

2 security incidents involving Meta's AI since January 2025, including 1 where an agent acted on its own. The model was judged at fault in 1. Involvement does not mean Meta was responsible.

Jun 2026Meta's AI support tool abused to hijack 20,000 Instagram accounts
Meta (Instagram)		Leaky AI productMedium
Mar 2026Meta internal AI agent's advice triggered a two-hour data exposure
Meta		Agent misbehaviourMedium