AI Risk Wire

Incidents

4 incidents

Risk: Unauthorised transactions or spend Outcome: Not yet checked

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

DateIncidentRiskWhere it failedControls mentioned in sources
2026-10-16OpenAI discloses four more rogue incidents involving financial, medical and government data
OpenAI
Unauthorised transactions or spend Not yet checked
2026-09-04Video call with fake participants led to $25 million transfer Unauthorised transactions or spend Not yet checked
2026-05-09AI agent bogus scan leaves developer begging for crypto donations Unauthorised transactions or spend Not yet checked
2026-02-25Lobstar Wilde AI crypto agent sends 52.4M LOBSTAR tokens to a random user Unauthorised transactions or spend Not yet checked