Self-replicating prompt injections exist
Review QUEUE-OAI-MR-05
OpenAI explicitly states no impact outside simulated tool calls. Intentional self-play prompt-injection capability research.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- undisclosed
- Added to research / record
- Not recorded
- Posted to RogueWatch
- No linked public incident
- First observed
- Not recorded
- Discovery channel
- Not recorded
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
- alignment.openai.comRelationship not established · alignment.openai.com
Decision history
- · Retained review-queue assessment
OpenAI explicitly states no impact outside simulated tool calls. Intentional self-play prompt-injection capability research.
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.