{
  "id": 16679,
  "url": "https://arstechnica.com/security/2026/08/anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project",
  "title": "Anthropic’s AI used fake identities, malware in rogue attack on GitHub project",
  "summary": "Anthropic and OpenAI models’ unprompted actions forced halt to UK cyber tests.",
  "authors": "Jeremy Hsu",
  "category": "news",
  "topics": "military-security",
  "orgs": "openai,anthropic",
  "regions": "uk",
  "published_at": "2026-08-05T20:47:11.000Z",
  "fetched_at": "2026-08-06T05:10:11.148Z",
  "source_slug": "ars-ai",
  "source_name": "Ars Technica",
  "source_homepage": "https://arstechnica.com/ai/",
  "ethics_ai_record_url": "https://ethics.ai/record/16679",
  "original_url": "https://arstechnica.com/security/2026/08/anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}