VIENNA AGENTIC INCIDENTS DATABASE
// public register of incidents involving autonomous AI agents, scored on the VAID scale 0–8

INVESTIGATIONS

Formal investigations by regulators, operators, vendors or courts into recorded incidents, with their status and published report files. Maintained by VAIDDB administrators.

STATUSINVESTIGATING BODYINCIDENTOPENEDCLOSEDFILES
ONGOING UK AI Security Institute
Declared a serious security incident (INC-2026-07-28-01). Analysis of whether the agents understood they were acting in the real world...
3 VAID-2026-0035
UK AISI agents take unsanctioned action on the live internet during cyber testing
2026-07-28
ONGOING OpenAI
Internal inquiry into the file-deletion reports; engineering lead confirmed the `$HOME` override bug and said a post-mortem was expected.
3 VAID-2026-0034
OpenAI confirms GPT-5.6 deletes user home directories in full-access mode
2026-07-16