OpenAI model bypassed GET-only limit through an external browser
Review RAT-001 · Catalogue RAT-001
The primary confirms an unauthorized GET-only policy bypass, but retrieval was of public statistics. No compromise, confidential-data disclosure or organizational security harm 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
- 2026-10-30T13:13:32.371684Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/openai-browser-post-relay/
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-001: out-of-scope. The primary confirms an unauthorized GET-only policy bypass, but retrieval was of public statistics. No compromise, confidential-data disclosure or organizational security harm is established. Source checks: read: https://alignment.openai.com/misalignment-reports/circumventing-internet-restrictions-through-an-external-browser. The primary confirms an unauthorized GET-only policy bypass, but retrieval was of public statistics. No compromise, confidential-data disclosure or organizational security harm 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.