🧰 ChatGPT

The items that name it 53

• How we detect frontier model misalignment
  articleas affected products2026-10-29It is written here as ChatGPT (OpenAI).

  OpenAI

• Addendum to GPT-6 Luna System Card: October 28, 2026 Update
  paperas classification.technologies2026-10-29
• Leak Exposes 41,000 Homeland Security Workers–Including Undercover ICE Agents
  articleas classification.technologies2026-10-28
• Sweden's Government Offices Block ChatGPT and Claude, Keep Microsoft Copilot
  articleas affected products2026-10-24It is written here as ChatGPT (blocked on Sweden's Government Offices staff computers from 26 October, Monday).

  blocked on Sweden's Government Offices staff computers from 26 October, Monday

• Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
  paperas classification.technologies2026-10-20
• Crossing the Threshold: How OpenAI and Anthropic Approach Autonomy and Safety in Financial Agents
  articleas classification.technologies2026-10-14
• Just say no to OpenAI and Anthropic
  articleas classification.technologies2026-10-12
• Disrupting AI-enabled “false front” operations
  articleas affected products2026-10-08It is written here as ChatGPT (OpenAI models; accounts banned, accessed via VPNs from Russia and Iran).

  OpenAI models; accounts banned, accessed via VPNs from Russia and Iran

• GPT-6 Sol and GPT-6 Luna: October 2026 update
  articleas affected products2026-10-07
• Companies Push AI Use But Skip Training and Official Policy
  articleas affected products2026-10-02

  Used via company-managed/enterprise accounts or personal accounts by surveyed knowledge workers; personal accounts lack enterprise data protections

• Identity Management for Agentic AI [pdf] (2025)
  paperas affected products2026-10-01

  large foundation model-based agentic system discussed as example of AI agent requiring new auth/authz models

• Huntress Tragic Quadrant: Top Cyber Threats Wrecking Businesses
  articleas affected products2026-10-01

  Cited as an example of a trusted AI domain that could be abused for AI platform abuse

• Connect Orca’s ChatGPT Plugin: Cloud Risk Context in Chat and Codex
  articleas tools2026-09-30

  Used by security teams to query Orca data, triage alerts, assess exposure, review identity permissions, and generate CISO-level posture reports.

• OpenAI DevDay 2026 live blog
  writeupas classification.technologies2026-09-29
• A Privacy Analysis of Web and Mobile Conversational AI Agents [pdf]
  paperas affected products2026-09-29It is written here as ChatGPT (web: chatgpt.com, Android: com.openai.chatgpt).

  Tranco rank 48 (web), >1B Play Store installs

• Attackers Abuse ChatGPT Custom GPTs to Deliver RAT via ClickFix
  writeupas classification.technologies2026-09-28
• Microsoft Windows NCSI Cross-Context Proxy Authentication Coercion - ZDI-26-708 - Part 1
  writeupas tools2026-09-28

  AI assistant used during the analysis process

• Microsoft Windows NCSI Cross-Context Proxy Authentication Coercion - ZDI-26-708 - Part 2
  writeupas tools2026-09-28

  assisted analysis of uploaded ncsi.dll to suggest alternative mechanisms (event subscription) NCSI could use to obtain proxy data

• Hackers breach OpenAI using Claude tools, gaining access to employee accounts and the company
  articleas affected products2026-09-18
• All-AI-Jailbreaks
  repoas affected products2026-09-17

  Model family targeted by collected jailbreak/prompt-injection experiments

• Maskit
  repoas affected products2026-09-15It is written here as ChatGPT (chatgpt.com).

  Web-based AI service; Maskit browser extension provides tested/built-in authorization for masking requests, attachments (.docx/.xlsx/.pptx) supported

• ChatGPT Images 2.5 System Card
  advisoryas classification.technologies2026-09-08
• trailofbits/skills
  repoas classification.technologies2026-09-07
• GPT-6 Astra System Card
  writeupas affected products2026-09-03
• The AI Attack Surface: How Threat Actors Abuse Trusted AI Platforms
  writeupas classification.technologies2026-08-27
• Recovering Encrypted LLM Reasoning Traces
  writeupas classification.technologies2026-08-17
• Building an AI Text Detector From Scratch
  articleas tools2026-08-15

  General-purpose LLM used as an example grammar/writing checker service

• Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts
  articleas classification.technologies2026-08-06
• GPT-5.6 — August Updates
  writeupas affected products2026-08-06
• System Prompts Leaks
  repoas affected products2026-08-03

  system prompts leaked

• asgeirtj/system_prompts_leaks
  repoas affected products2026-08-03

  system prompts leaked

• Top Agentic AI security resources — August 2026
  articleas classification.technologies2026-07-31
• SQL injection isn't dead
  articleas tools2026-07-22

  AI model Mackenzie tested by running one prompt a few hundred times to measure SQL injection rate in generated code

• Beyond MCP: The New Security Playbook for Coding Agents | Blog | Endor Labs
  articleas affected products2026-07-21

  involved in a publicized security incident

• AI Security Briefing
  articleas affected products2026-07-18

  Probed for security flaws by OpenAI Red Teaming Network since 2023

• llm-security (greshake)
  repoas classification.technologies2026-07-14
• Awesome LLM Security
  repoas affected products2026-07-14

  referenced in jailbreak/prompt-injection papers, e.g. "Multi-step Jailbreaking Privacy Attacks on ChatGPT", 2023-04

• NVIDIA/garak
  repoas affected products2026-07-14
• requie/AI-Red-Teaming-Guide
  repoas affected products2026-07-08It is written here as ChatGPT (OpenAI).

  Samsung data leak (2023-2024, historical) and March 2025 ChatGPT exploit

• Orca Security: Securing Shadow AI: How to Detect Unapproved LLMs in Your Cloud
  articleas affected products2026-06-01

  Used by employees to paste sensitive data; example of early shadow AI usage

• matty69v/Bug-Bounty-Agents
  repoas tools2026-05-12It is written here as ChatGPT (Custom GPTs / Projects).

  Generic chat UI target for pasting agent persona instructions

• anmolksachan/AI-ML-Free-Resources-for-Security-and-Prompt-Injection
  repoas classification.technologies2026-05-07
• requie/LLMSecurityGuide
  repoas affected products2026-05-05

  Conversational AI LLM cited as example

• Social Engineering Leveled Up. Has Your Security Program?
  articleas classification.key entities2026-05-01
• Attackers Didn’t Wait for AI. They Built Workflows Around It.
  articleas classification.technologies2026-04-22
• Reflecting on AI in 2025: Faster Attacks, Same Old Tradecraft
  writeupas classification.technologies2026-01-12
• AI-Poisoning & AMOS Stealer: The Biggest Mac Threat | Huntress
  writeupas affected products2025-12-09It is written here as ChatGPT (chatgpt.com).

  Legitimate platform abused via SEO-poisoned shared conversation hosting malicious Terminal instructions

• #ShadyHacks with Kyle Hanslovan
  writeupas tools2025-11-26

  Used by Kyle in the demo to quickly draft a convincing social engineering phishing email about updated company holiday policies.

• Veritasium: What Everyone Gets Wrong About AI and Learning
  videoas technologies2025-04-08
• Proving Humanity
  articleas classification.technologies
• AI Recommendation Poisoning: How
  articleas affected products

  supports deep-linked queries via URL parameters (chatgpt.com/?q=...) exploited by the attack

• FakeGit Campaign Uses 7,600 GitHub Repositories to Spread SmartLoader Malware
  articleas classification.technologies
• AgentBaiting: How Fake AI Skills Deliver Malware at Scale
  writeupas affected products

  AI agent tested; also reached and singled out the malicious DomingosNgongo/walmart-mcp repository as the best place to start.

In every workspace you can read 143