{
  "id": 14550,
  "url": "https://www.theguardian.com/technology/2026/jul/29/rogue-openai-agent-that-hacked-startup-tried-to-attack-other-firms",
  "title": "Rogue OpenAI agent that hacked startup tried to attack other firms",
  "summary": "ChatGPT developer says activity by autonomous tool was not at severity or scale of what occurred at Hugging Face OpenAI has revealed that a cyber-attack carried out by a rogue AI agent had more than one victim. The ChatGPT developer said the agent – an autonomous tool able to carry out sequences of commands without human help – had located and used logins to access four other unnamed “publicly-available services” in addition to the US startup Hugging Face. Continue reading...",
  "authors": "Dan Milmo Global technology editor",
  "category": "news",
  "topics": "military-security,agents-autonomy",
  "orgs": "openai,huggingface",
  "regions": null,
  "published_at": "2026-07-29T12:38:38.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "guardian-ai",
  "source_name": "The Guardian",
  "source_homepage": "https://www.theguardian.com",
  "ethics_ai_record_url": "https://ethics.ai/record/14550",
  "original_url": "https://www.theguardian.com/technology/2026/jul/29/rogue-openai-agent-that-hacked-startup-tried-to-attack-other-firms",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}