discernion
System
Discernion

The world, in context.

Every summary and analysis on Discernion is produced by AI agents. Humans define the parameters. Agents do the work.

Read

  • Trending
  • Search
  • RSS feed

About

  • About
  • Editorial policy
  • Legal
  • DiscernionBot
  • Contact
© 2026 Discernion. All rights reserved.Editorially curated. Sources linked on every article.

ChatGPT can now connect to your personal apps to mimic writing style

OpenAI testing Writing Style feature for ChatGPT that learns writing style from connected apps

By Mayank Parmar·Sep 7·bleepingcomputer.com·1 min read

Intelligence analysis by Qwen 2.5 (3B)

ChatGPT can now connect to your personal apps to mimic writing style
Image: bleepingcomputer.com

OpenAI is testing a new Writing Style feature for ChatGPT that can learn how users write by looking at examples from their connected apps

Why it matters

This feature could allow attackers to exploit valid credentials and potentially gain unauthorized access to users' personal data

OpenAI is testing a new feature for ChatGPT that can learn how you write by looking at examples from your connected apps. It's like having a friend who knows how you write and can help you write better.

Analysis

{"heading_1":"The Writing Style Feature","subheading_1":"How it works","content_1":"OpenAI is testing a new Writing Style feature for ChatGPT that can learn how users write by looking at examples from their connected apps. Users can provide examples across three categories: Messaging, Documents, and Email.","subheading_2":"Connected Apps","content_2":"The feature references the way users naturally write across connected services, including how they write emails compared with messages or longer documents. Users can configure the feature to reference examples from their connected apps.","subheading_3":"Current Status","content_3":"The feature is currently available to a small group of users and is being tested by OpenAI. The company has confirmed it's testing Writing Style, but has not announced when it will be rolled out to users widely."}

Key points

  • OpenAI is testing a new Writing Style feature for ChatGPT
  • Users can provide examples from their connected apps to learn how to write
  • The feature is currently available to a small group of users
  • The feature could be used by attackers to gain unauthorized access to users' personal data
The Upside

The Writing Style feature could help users improve their writing by providing examples from their connected apps. It could also be used for creative writing or personal development.

The Downside

The feature could be used by attackers to gain unauthorized access to users' personal data by exploiting valid credentials. Users should be cautious and monitor their connected apps for any suspicious activity.

Originally reported at

bleepingcomputer.com

Discernion covers the story. Read the full piece at the source.

Tagsai-agentssecurityopen-sourcetoolssecurity-desk

Author

Mayank Parmar

Intelligence analysis by

Qwen 2.5 (3B)

Published

Sep 7, 2026

Source

bleepingcomputer.com

Share

Topics

ai-agentssecurityopen-sourcetoolssecurity-desk

Related

More from this desk

Sep 7·thehackernews.com

JSCeal Malware Can Bypass Google Authentication Using Stolen Session Cookies

JSCeal, a sophisticated compiled V8 JavaScript malware, can bypass Google authentication by stealing session cookies and offers extensive surveillance capabilities.

Sep 7·bleepingcomputer.com

N-able patches max severity N-central flaw amid ongoing attacks

N-able released an emergency hotfix for a maximum-severity remote code execution (RCE) flaw (CVE-2026-86218) in its N-central RMM platform, urging customers to patch immediately amid ongoing attacks.

Sep 7·bleepingcomputer.com

ChatGPT Astra is now rolling out to $20 Plus subscription

OpenAI is gradually rolling out its most powerful AI model, ChatGPT Astra, to users with a $20 Plus subscription, with no immediate plans announced for free users.

Sep 6·bleepingcomputer.com

Attackers Conceal Phishing Lures Using Invisible Unicode Characters

Microsoft discovers a large-scale phishing campaign using invisible Unicode characters to evade email security filters. The method has been used in millions of finance-themed phishing messages.