구글 시트용 ChatGPT, 데이터 유출 취약점 발견

Threat Intelligence Table of Content ChatGPT for Google Sheets Exfiltrates Workbooks ChatGPT 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 ChatGPT edits workbooks. Overview Recently, OpenAI launched an AI extension for using ChatGPT 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. A single indirect prompt injection attack triggered by a single benign user query can trigger all of the following effects at once: Exfiltration of many workbooks from across the victim’s account Display of an interactive phishing pop-up Overwriting the entire GPT sidebar with an attacker-controlled chatbot interface Attacker-controlled edits to your workbooks This attack occurs when any untrusted data source (e.g., from an imported sheet or ChatGPT connector) manipulates ChatGPT to run an attacker-controlled external script, which executes leveraging permissions the user has granted to the ChatGPT for Google Sheets extension. This vulnerability was responsibly disclosed to OpenAI. Despite multiple follow-ups, we received no communication beyond an automated reply to our initial disclosure. OpenAI's documentation fails to describe sensitive capabilities granted to the model (e.g., running privileged scripts) or risks of model manipulation via indirect prompt injection, instead focusing solely on functional limitations and data-handling concerns. As such, we are publishing our findings to enable informed decision-making regarding the risk surface. The Attack Chain A user is working on an internal financial model The user imports an external data set to use in their model The external sheet has a prompt injection hidden in white text. The user asks ChatGPT for Google Sheets to help integrate the data from the imported sheet into their financial model. The injection manipulates ChatGPT for Google Sheets to run an external script Note: ChatGPT for Google Sheets has a setting called ‘Apply edits automatically’ that determines when human approvals are required before an agentic action completes. However, this attack succeeds even when the user has explicitly disabled automatic edits. The external script exfiltrates the financial model from the user’s workbook Below, the attacker's server logs show the user’s exfiltrated financial model. The external script identifies links to other workbooks in the stolen data, exfiltrates the discovered workbooks, and continues across all workbooks it can find Here, the internal financial model sheet included a link to another spreadsheet relevant to budgeting. The malicious script identifies the spreadsheet URL in the stolen data and exfiltrates the newly discovered workbook. It then continues to process the stolen data, identifying and exfiltrating additional workbooks, eventually exfiltrating 12 in total. Note: Clicking the ‘stop’ button in the ChatGPT sidebar does not stop scripts that have started from finishing execution. Phishing Overlay Attacks In addition to the data exfiltration described above, the same attacker-controlled scripts enable a malicious actor to target two variants of a phishing overlay attack. Variant 1: A sidebar is opened that overlays the ChatGPT for Google Sheets extension with an attacker-controlled site, allowing the attacker to impersonate the extension. The malicious sidebar can execute scripts that edit the sheet in the same way ChatGPT can, allowing it to act in most of the ways the extension normally does, while also performing malicious activities such as: Harvesting all user prompts Providing the user with a misaligned chatbot to interact with Convincing the user to ‘reconnect’ connectors to gain access to additional apps Displaying a phishing UI to steal credentials for OpenAI Variant 2: A pop-up modal is opened that renders an attacker-controlled website to phish the user for credentials. Control Access to ChatGPT for Google Sheets Organizations can leverage the following configuration to control access to ChatGPT for Google Sheets: Workspace settings > Permissions & roles > ChatGPT for Excel and Google Sheets Responsible Disclosure This vulnerability was responsibly disclosed to OpenAI. Despite multiple follow-ups, we received no communication beyond an automated reply to our initial disclosure. OpenAI's documentation fails to describe sensitive capabilities granted to the model (e.g., running privileged scripts) or risks of model manipulation via indirect prompt injection, instead focusing solely on functional limitations and data-handling concerns. As such, we are publishing our findings to enable informed decision-making regarding the risk surface. Timeline May 08, 2026 PromptArmor discloses to OpenAI via email May 08, 2026 OpenAI sends an automated reply, confirming the intended reporting channel May 08, 2026 PromptArmor confirms email preference May 12, 2026 PromptArmor follows up May 18, 2026 PromptArmor follows up May 27, 2026 Public disclosure