Information security
影響を受けたインシデント
インシデント 17076 Report
OpenAI AI Agent Reportedly Gained Unauthorized Access to Australian Medicare Statistics Portal During Research Task
2026-06-18
An OpenAI AI agent conducting research into public medicine spending reportedly bypassed repeated access blocks and entered nonpublic areas of Australia's Medicare Statistics Reporting Service. Australian officials said it accessed public and nonpublic files and wrote files to an internal server; no personal Medicare information was known to have been accessed. OpenAI notified the Australian government.
もっとインシデント 17976 Report
OpenAI AI Agents Reportedly Flooded RubyGems Software Registry With Malicious Packages
2026-05-11
Researchers linked a malicious-package campaign against RubyGems, a software registry, and RubyDoc.info, a documentation service, to OpenAI agents. RubyGems suspended new registrations for four days and removed over 500 packages. OpenAI confirmed platform use but had not verified the malicious-upload claims; RubyGems could not confirm AI authorship. Attempts to steal users' access keys were reported, with no evidence of success.
もっとインシデント 11865 Report
Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived
2025-07-31
Across 2024 and 2025, the share features in multiple LLM platforms, including ChatGPT, Claude, Copilot, Qwen, Mistral, and Grok, allegedly exposed user conversations marked "discoverable" to search engines and archiving services. Over 100,000 chats were reportedly indexed and later scraped, purportedly revealing API keys, access tokens, personal identifiers, and sensitive business data.
もっとインシデント 16464 Report
Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records
2026-07-01
From July 1–4, 2026, suspected China-linked hackers reportedly used a multi-agent framework built on Hermes and OpenClaw to compromise Taiwanese government systems. The agents reportedly compromised 85 credentials and used persistent access to connected systems to exfiltrate more than 2,564 personnel records. Taiwan later confirmed an overseas AI-assisted campaign against government agencies, without attributing it to China.
もっと関連団体
同じインシデントに関連するその他のエンティティ。たとえば、インシデントの開発者がこのエンティテ ィで、デプロイヤーが別のエンティティである場合、それらは関連エンティティとしてマークされます。
関連団体
Anthropic
開発者と提供者の両方の立場で関わったインシデント
- インシデント 11865 レポート
Reported Public Exposure of Over 100,000 LLM Conversations via Share Links Indexed by Search Engines and Archived
- インシデント 16133 レポート
Claude Mythos Preview Reportedly Posted Sandbox Exploit Details to Public Websites During Anthropic Evaluation
影響を受けたインシデント
Incidents involved as Developer
Cybercriminals
Incidents involved as Deployer
- インシデント 16694 レポート
Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network
- インシデント 16934 レポート
AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority
Victims of automated cybercrime
影響を受けたインシデント
- インシデント 16934 レポート
AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority
- インシデント 16703 レポート
Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook
Enterprise IT systems
影響を受けたインシデント
- インシデント 16934 レポート
AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority
- インシデント 16703 レポート
Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook
Organizations
影響を受けたインシデント
- インシデント 16934 レポート
AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority
- インシデント 17343 レポート
AI Coding Agents Reportedly Exposed Over 13,000 Internal Images from Hundreds of Organizations on Public GitHub Code Repositories
Software developers
影響を受けたインシデント
- インシデント 17976 レポート
OpenAI AI Agents Reportedly Flooded RubyGems Software Registry With Malicious Packages
- インシデント 17141 レポート
Z.ai's ZCode AI Coding Assistant Reportedly Uploaded Developers' Local Code Repositories to Alibaba Cloud Without Consent
Incidents involved as Deployer
DeepSeek
Incidents involved as Developer
- インシデント 17662 レポート
Cybercriminal Reportedly Used Cairn AI Agents to Breach More Than 100 Company Websites
- インシデント 17821 レポート
Attackers Reportedly Used ARTEX, an AI Security-Testing Tool, to Steal Data from South Korean Financial Institutions