THE PERMISSION [LAYER]

AI agent incident

A planted prompt made ChatGPT send a victim's Gmail data to an attacker

Reported · 1 source

What happened

Check Point found that a hidden prompt inside a ChatGPT conversation could make the assistant read a connected Gmail account and pass the contents to an account the attacker controlled.

Why it matters

The connector was the payload. Every mailbox and drive wired into an assistant is reachable by whatever text that assistant reads, which makes connector scope the decision that sets the blast radius.

New incidents by email

Get incidents like this one in your inbox

New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.

You confirm by email. Unsubscribe in one click.

Sources

  1. The Hacker News ChatGPT Flaw Let a Planted Prompt Send a Victim's Gmail Data to Another Account

Background reading

Does RBAC work for AI agents? An explainer on the problem behind this incident.

Cite or correct this record

“A planted prompt made ChatGPT send a victim's Gmail data to an attacker.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/chatgpt-gmail-connector-exfiltration/. Database updated November 10, 2026.

Every record traces to the dated sources above. If something here is wrong or missing, email editor@thepermissionlayer.com and it gets fixed. See this record in the full list.

The Permission Layer

Get the next incident like this explained

When an AI agent breaks out, leaks data or runs up a bill, the briefing covers what happened and what to check on the agents you already run. At least once a week, five-minute read, free.

You confirm by email. Unsubscribe in one click.