Like many others, my feed was also quickly taken over by the excitement around ChatGPT. I must confess, I am also excited about this, and I have a few ideas of my own. Ideas of integrations abound – let’s create a bot that automatically summarizes twitter threads. Let’s create a bot to summarize whatsapp convesations. Let’s create a bot that will answer questions in conversations, and so on and so on.
With that, many people also showed various “hacks” – getting ChatGPT to respond in an unaligned manner, or printing out its original prompt that OpenAI gave it, etc.
Inevitably, some people plugged it in to Google Sheets. Nice! Indeed it is impressive. However, let’s combine the two ideas. Very simply, I used one of the integrations from the link above:

The implications are obvious, without some proper anti-injection techniques, the output from GPT integrations may be unsafe, especially if the output is piped into a scripting enabled environment.
Leave a Reply