AI Risk WireCommands: AI incidents
What has gone wrong with AI systems, where, and how badly.
Incidents, Oct 2026
Average of the 3 months before: 0.3
Major and severe incidents, Oct 2026
Average of the 3 months before: 0.3
All incidents
2 of 734 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 reported | Incident | Risk | AI developer | Severity |
|---|---|---|---|---|
| 2026-11-06 | ThisBash: malicious browser extension drives Claude Desktop Dispatch to run commands (researcher proof of concept) Preliminary | AI used to run a cyber attack Security compromise | Anthropic | minor |
| 2026-09-21 | Researchers break out of OpenAI Codex sandbox twice Preliminary | Hidden instructions hijack the agent Security compromise | OpenAI | major |
Browse incidents by
Search pages: AI cyberattacks (103) · Prompt injection incidents (49) · AI agent incidents (80) · AI lawsuits (73)