AI Incident Database #473 · 2023-02-08
Bing Chat's Initial Prompts Revealed by Early Testers Through Prompt Injection
Early testers of Bing Chat successfully used prompt injection to reveal its built-in initial instructions, which contains a list of statements governing ChatGPT's interaction with users.
- Risk class (MIT)
- AI system security vulnerabilities and attacks
- Reports
- 1
- Developers and deployers named
- 2
On ShieldMap: Microsoft, OpenAI (named by AIID as a developer or deployer).
Reports
- AI-powered Bing Chat spills its secrets via prompt injection attack [Updated] · arstechnica.com, 2023-02-10
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.