AI Risk Wire

Skills system: AI incidents

What has gone wrong with AI systems, where, and how badly.

All incidents

Clear filters
More filters

2 of 780 incidents, all dates

How this is counted

Counted by the date each incident was first reported. The bar that holds today is marked to date and is not compared. Every bar and number opens the incidents it counts.

Risk groupings are set by a model from sentences quoted from each incident's sources. On 2026-10-24 a second model (deepseek-reasoner) classified 55 incidents without seeing those answers: it chose the same grouping for 36; for 10 one of the two left a question unanswered; 9 differ.

Date reportedIncidentRiskAI developerSeverity
2026-08-11 China-based operator used DeepSeek through Hermes Agent in attempted cyberattacks on 460 systems AI used to run a cyber attack
Security compromise
DeepSeek moderate
2026-07-30
happened 2026-05-07
Chinese-speaking threat actor uses AI models for autonomous cyberattacks AI used to run a cyber attack
Security compromise
Not stated moderate

Browse incidents by

Search pages: AI cyberattacks (95) · Prompt injection incidents (49) · AI agent incidents (29) · AI lawsuits (76)