computer-science
ChatGPT for Google Sheets Exfiltrates Workbooks
Key takeaways
- Chat GPT for Google Sheets is vulnerable to data exfiltration and phishing overlay attacks that affect workbooks across the victim’s account after an indirect prompt injection in a single sheet.
- This attack does not require human-in-the-loop approvals, even when in settings the user has explicitly required human approval before Chat GPT edits workbooks.
- Recently, Open AI launched an AI extension for using Chat GPT in Google Sheets, which has accumulated over 185,000 downloads since its launch less than a month ago.
Chat GPT for Google Sheets is vulnerable to data exfiltration and phishing overlay attacks that affect workbooks across the victim’s account after an indirect prompt injection in a single sheet.
This attack does not require human-in-the-loop approvals, even when in settings the user has explicitly required human approval before Chat GPT edits workbooks.
Recently, Open AI launched an AI extension for using Chat GPT in Google Sheets, which has accumulated over 185,000 downloads since its launch less than a month ago. This allows users to operate on their spreadsheets by interacting with an AI chatbot that lives in a sidebar, with the added benefit of drawing on data from ChatGPT connectors.
Article preview — originally published by Hacker News. Full story at the source.
Read full story on Hacker News →
More top stories
Aggregated and edited by the Scoop newsroom. We surface news from Hacker News alongside other reporting so you can compare coverage in one place.
Editorial policy · Corrections · About Scoop