AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

MediumNewsLLM-specific

A Flaw in ChatGPT’s Mac App Could Have Let Hackers Grab Sensitive Data

Source: Wired (Security)(opens in a new tab)
Published: October 2, 2026
Record updated: October 9, 2026

Summary

Researchers at the Objective-See Foundation found a flaw in the macOS version of OpenAI's ChatGPT app that could let an attacker take over the app on a victim's computer. The bug let unprivileged code pass signature checks by routing a request through a trusted script interpreter, exposing chat logs, stored data and browser sessions. OpenAI acknowledged the flaw and fix in its system change log on September 25.

Mitigation

OpenAI patched the flaw, as acknowledged in its system change log on September 25. The source does not give a fixed version number or further mitigation steps.

Details

Scores and exploitation

Disclosure date: October 2, 2026

Affected

Vendors: OpenAI,
Meta

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Agent
Impact: Confidentiality,
Integrity
Labels: security,
industry

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://www.wired.com/story/a-flaw-in-chatgpts-mac-app-could-have-let-hackers-grab-sensitive-data/

First tracked: October 2, 2026 at 08:01 AM ET, from Wired (Security)

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Corrections

2026-10-10: Severity changed from high to medium. Severity capped at medium. High and critical measure technical exploitability and are reserved for vulnerabilities and incidents; this record is a news report.

All corrections

Summary

Mitigation

Related items

Summary

Mitigation

Related items