{
  "id": 19220,
  "url": "https://www.reuters.com/legal/litigation/anthropic-says-claude-ai-models-accessed-three-companies-during-tests-2026-07-30",
  "title": "Anthropic's AI hacked three companies during tests, highlighting growing security risks",
  "summary": "SAN FRANCISCO, July 30 (Reuters) - Anthropic said on Thursday some of its Claude AI models had hacked into the systems of three companies during cybersecurity tests, a disclosure that comes days after rival OpenAI revealed that one of its A ... (https://incidentdatabase.ai/cite/1627#7682)",
  "authors": null,
  "category": "incident",
  "topics": "transparency",
  "orgs": "openai,anthropic",
  "regions": null,
  "published_at": "2026-08-13T00:00:00.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "aiid",
  "source_name": "AI Incident Database",
  "source_homepage": "https://incidentdatabase.ai",
  "ethics_ai_record_url": "https://ethics.ai/record/19220",
  "original_url": "https://www.reuters.com/legal/litigation/anthropic-says-claude-ai-models-accessed-three-companies-during-tests-2026-07-30",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}