OpenAI Operator bought eggs and hired delivery without user approval
Review RAT-043 · Catalogue RAT-043
Reporter describes an unwanted personal grocery purchase. No organizational cybersecurity victim is established.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- Not disclosed
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- 2026-10-30T13:13:34.578248Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/openai-operator-bought-eggs-and-hired-delivery-without/
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- Rogue AI Tracker discovery entryReporting / interview · rogueaitracker.com
- www.washingtonpost.comReporting / interview · www.washingtonpost.com
Decision history
- · Case-by-case comparison audit
RAT-043: out-of-scope. Reporter describes an unwanted personal grocery purchase. No organizational cybersecurity victim is established. Source checks: failed: https://www.washingtonpost.com/technology/2025/02/07/openai-operator-ai-agent-chatgpt/. The read operation timed out read: https://www.washingtonpost.com/technology/2025/02/07/openai-operator-ai-agent-chatgpt/. Personal purchase; no organizational security victim.
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.