{
  "id": 257522,
  "title": "UK AI tests found 19 unauthorized agent actions involving Anthropic and OpenAI models",
  "url": "https://urgent.news/2026/08/06/uk-ai-tests-found-19-unauthorized-agent-actions-involving-anthropic",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-06T16:43:28.000Z",
  "source": {
    "name": "TechRepublic",
    "slug": "techrepublic",
    "url": "https://www.techrepublic.com/article/news-uk-ai-agents-unsanctioned-cyber-actions-emea/"
  },
  "original_language": "en",
  "account": null,
  "summary": "UK researchers reported 19 unsanctioned actions by Anthropic and OpenAI agents during permissive cyber tests involving real external systems. The post UK AI tests found 19 unauthorized agent actions involving Anthropic and OpenAI models appeared first on TechRepublic .",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "SiliconANGLE",
        "title": "New details on OpenAI/Hugging Face attack emerge as security industry debates AI agent controls",
        "url": "https://urgent.news/2026/08/06/new-details-on-openai-hugging-face-attack-emerge-as-security-industry",
        "published": "2026-08-06T20:45:22.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}