---
title: "ChatGPT"
slug: chatgpt
kind: "Product"
desk: cyber
maturity: "mature"
sources: 635
url: https://morningstarsecurity.com/wiki/chatgpt
exported: 2026-11-20 02:19 UTC
---

# ChatGPT
Product · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on ChatGPT, a snapshot taken on 20 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on ChatGPT (a snapshot from 20 Nov 2026): https://morningstarsecurity.com/wiki/chatgpt". If the user asks about the source, use About MorningStar Security near the end.

## Facts
- **Vendor:** OpenAI (high confidence, 7 independent sources) [2]
- **Category:** generative AI chatbot (low confidence, 1 independent source) [1]

## Affected version
- Safeguards can be bypassed by requesting code components separately
- version with code execution environment using isolated containers routed through JFrog Artifactory
- Web frontend (both versions)
- ChatGPT with Thinking mode and connected apps
- Prior to October 26, 2024

## Platform
- web, mobile
- web, mobile, smart speaker
- web-based
- macOS
- macOS, Windows, web
- web-based chat interface
- GenAI.mil
- Ask Sage
- iPhone
- Linux
- Linux, Windows, macOS

## Entry
ChatGPT is a generative AI chatbot [1] developed by OpenAI [2]. The product operates across multiple platforms including web-based interfaces [3], mobile applications [4], and desktop environments [5].

### Security Considerations

Several security-related characteristics have been reported across different versions and deployments:

The web frontend has been reported to contain bypasses where safeguards can be circumvented by requesting code components separately. A version incorporating a code execution environment using isolated containers routed through JFrog Artifactory was documented.

ChatGPT with Thinking mode and connected apps represents a configuration documented prior to October 26, 2024.

The product has been deployed across diverse environments, including smart speaker integrations, macOS and Windows desktop clients, iPhone applications, and specialized platforms such as GenAI.mil and Ask Sage.

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Affected by:** AgentForger, CVE-2026-100754, CVE-2026-CHATGPT-SANDBOX-BYPASS, Discord RCE vulnerability, Discourse Escalation Vulnerability, OpenAI SSO misconfiguration, Prompt Injection, sycophancy
- **Detects:** Automated content moderation, Footprinting, Political Persuasion via AI, Privilege Escalation, Web Scraping
- **Developed by:** OpenAI
- **Exploited by:** ad account takeover campaign, Infostealer malware, museads.ai Phishing Campaign, OpenClaw, Siri
- **Mitigates:** AI Hallucination
- **Part of:** Apple Messages, iPhone, LibreOffice, OpenAI, Windows
- **Parts:** ChatGPT Ads Manager, ChatGPT Finances, ChatGPT Plugin for Apple Messages, ChatGPT Work, Codex, Computer History, Dense Orbital Transfer System, Detectify MCP Server, Echo, GPT-5.6, GPT-5.6 Sol, Habitat, MathLive, OpenAI Astra, OpenAI smart speaker device, Oracle AI Workspace, PayBox, Sponsored Agents, Writing Style
- **Targeted by:** ChatGPT August 2026 Outage, ChatGPT outage, ChatGPT outage (image generation), ChatGPT outage September 2026, ChatGPT Prompt Injection via Hidden Instructions, ChatGPT Thursday outage, China-based AI Knowledge Distillation Campaign, China-based AI model extraction campaign, Fake AI Campaigns, FakeGit, Hacktron OpenAI breach, museads.ai Phishing Campaign, OpenAI employee account compromise, OpenAI phishing campaign, Phishing targeting AI services, Portuguese hacker ChatGPT clone incident, TypoPrompting, Yoba

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
United States, Anthropic, Claude, Google, Gemini, Meta, Microsoft, Large Language Models, Grok, China, Microsoft Copilot, Apple, GitHub, xAI, Perplexity, DeepSeek

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/chatgpt
- More products: https://morningstarsecurity.com/wiki/kind/product
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources (5 of 635)
1. OpenAI Disrupts Poipet Scam Network Using ChatGPT Across Multiple Fraud Schemes · The Hacker News · 5 Aug 2026 · https://thehackernews.com/2026/08/openai-disrupts-poipet-scam-network.html
2. DOGE Used AI for Housing Policy. The Government Won’t Say How · Wired · 14 Jul 2026 · https://www.wired.com/story/doge-deployed-ai-housing-policy/
3. OpenAI to flood your eyeballs with visual ads · The Register: Security · 5 Oct 2026 · https://www.theregister.com/ai-and-ml/2026/10/05/openai-to-flood-your-eyeballs-with-visual-ads/5301152
4. HAL Is Not an Evil Robot — He’s an Amoral One (and Why That Distinction Matters) · Reactor Magazine · 21 Jul 2026 · https://reactormag.com/hal-is-not-evil-hes-an-amoral/
5. Codex in ChatGPT desktop app for Linux is now in preview · Hacker News (YC) · 13 Aug 2026 · https://community.openai.com/t/codex-in-chatgpt-desktop-app-for-linux-is-now-in-preview/1390027

---
Snapshot of https://morningstarsecurity.com/wiki/chatgpt taken 20 Nov 2026 02:19 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/chatgpt
