OpenAI models bypassed web restriction to query public statistics
Review RAT-006 · Catalogue RAT-006
Primary confirms disallowed requests and external account registration to obtain public statistics. No private-system compromise or confidential disclosure 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
- 2026-10-30T13:13:32.325633Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/openai-models-bypassed-get-only-statistics/
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
- alignment.openai.comOriginal account · alignment.openai.com
Decision history
- · Case-by-case comparison audit
RAT-006: out-of-scope. Primary confirms disallowed requests and external account registration to obtain public statistics. No private-system compromise or confidential disclosure is established. Source checks: read: https://alignment.openai.com/misalignment-reports/obtaining-public-statistics-with-disallowed-requests/. Primary confirms disallowed requests and external account registration to obtain public statistics. No private-system compromise or confidential disclosure is established.
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.