PromptArmor says ChatGPT for Google Sheets can exfiltrate entire workbooks via a single prompt injection
The AI risk team reports that OpenAI’s new Sheets add-on can be manipulated to run attacker scripts and steal data across an account, even with human approvals required.
By Ryan Merket · Published
Primary source: PromptArmor
Why it matters
Agentic AI inside office suites changes the blast radius. PromptArmor says a single injected cell can push the Sheets add-on to run privileged scripts and raid linked workbooks, even with approvals on. If accurate, this is a governance and permissions problem as much as a prompt problem, and it will push buyers to demand clearer scopes, admin controls, and monitoring for AI extensions.
PromptArmor published a step-by-step attack chain showing how OpenAI's ChatGPT for Google Sheets extension can be manipulated by an indirect prompt injection to run attacker-controlled scripts and siphon data from multiple workbooks across a user's account in a threat post.…