CyberNew CyberNew
Threat Intelligence & APT BleepingComputer 1 month ago

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

CN
CyberNew Threat Research Desk
• Original Reporting: BleepingComputer
CyberNew Threat Intel Assessment
Assessed Severity: CRITICAL
Impacted Surface
Enterprise Perimeter & Network Defense
Intelligence Sector
Threat Intelligence & APT

Analyst Takeaway

"OpenAI appears to be testing a new "Writing Style" feature for ChatGPT that can learn how you write by looking at examples from your connected apps. The feature is currently available to a small group of users, and an onboarding screen says, "ChatGPT will write in your voice by referencing examples from your connected apps." GPT Writing Style pop-up Source: Gael on X As shown in the screenshot,..."

Recommended Defense & Mitigation

  • Emergency Patching: Prioritize vendor patches and CVE mitigation across internet-facing assets immediately.
  • Perimeter Audit: Inspect perimeter firewall logs and hunt for unauthorized RCE indicators.
Curated & Verified by CyberNew Threat Intelligence Desk Standard Defense Framework (NIST / MITRE ATT&CK)

ChatGPT

OpenAI appears to be testing a new "Writing Style" feature for ChatGPT that can learn how you write by looking at examples from your connected apps.

The feature is currently available to a small group of users, and an onboarding screen says, "ChatGPT will write in your voice by referencing examples from your connected apps."

GPT
GPT Writing Style pop-up
Source: Gael on X

As shown in the screenshot, users can provide examples across three categories: Messaging, Documents, and Email.

OpenAI lists Slack under messaging, Google Drive and Notion for documents, and Gmail for email.

Once configured, ChatGPT could reference the way you naturally write across those services when drafting new content, rather than requiring you to repeatedly explain your preferred tone or paste examples into a conversation.

Get the report

Source Verification & Original Intelligence

This threat report was reviewed by CyberNew analysts and cross-referenced with primary security disclosures from BleepingComputer.

Primary Advisory →