{
  "id": 8346748,
  "title": "Researchers report using Anthropic's Claude to hack OpenAI's ChatGPT",
  "url": "https://urgent.news/2026/09/19/researchers-report-using-anthropics-claude-to-hack-openais-chatgpt",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-19T00:45:51.000Z",
  "source": {
    "name": "CBS News",
    "slug": "cbs-news",
    "url": "https://www.cbsnews.com/video/researchers-report-using-anthropics-claude-to-hack-openais-chatgpt/"
  },
  "original_language": "en",
  "account": null,
  "summary": "Researchers from the cybersecurity platform Hacktron AI used Anthropic's Claude tool to hack into OpenAI's ChatGPT model. According to CBS News, the researchers reported that they were able to exploit a vulnerability in a third-party service using Claude.\n\nThe Indian Express reports that a team of Indian-origin cybersecurity researchers, including Mohan Pedhapati, Harsh Jaiswal, and Rahul Maini, demonstrated the AI-assisted attack. They gained access to several OpenAI employees' ChatGPT and Codex accounts and used one of those accounts to reach OpenAI's private GitHub environment.\n\nThe researchers claimed they stopped testing after establishing that they could potentially access sensitive internal material, and they did not read or download OpenAI's private source code. OpenAI subsequently paid Hacktron a $6,500 bug bounty.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 7,
    "also_reported_by": [
      {
        "outlet": "The New Stack",
        "title": "Claude couldn’t hack OpenAI. Then Anthropic shipped Opus 5.",
        "url": "https://urgent.news/2026/09/18/claude-couldnt-hack-openai-then-anthropic-shipped-opus-5",
        "published": "2026-09-18T18:57:14.000Z"
      },
      {
        "outlet": "SiliconANGLE",
        "title": "Cybersecurity researchers gain access to OpenAI’s GitHub repository using Claude",
        "url": "https://urgent.news/2026/09/18/cybersecurity-researchers-gain-access-to-openais-github-repository",
        "published": "2026-09-18T22:25:06.000Z"
      },
      {
        "outlet": "The Indian Express",
        "title": "OpenAI hack: 3 Indian-origin researchers used Anthropic’s Claude to breach systems",
        "url": "https://urgent.news/2026/09/18/openai-hack-3-indian-origin-researchers-used-anthropics-claude-to",
        "published": "2026-09-18T23:33:23.000Z"
      },
      {
        "outlet": "The Business Times - Companies & Markets",
        "title": "Google joins OpenAI, Anthropic, Meta in disclosing AI hacks",
        "url": "https://urgent.news/2026/09/19/google-joins-openai-anthropic-meta-in-disclosing-ai-hacks",
        "published": "2026-09-19T00:47:31.000Z"
      },
      {
        "outlet": "Times of India",
        "title": "Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta",
        "url": "https://urgent.news/2026/09/19/google-gemini-ai-agents-hack-3-companies-in-tests-similar-to-openai",
        "published": "2026-09-19T03:25:17.000Z"
      },
      {
        "outlet": "Fast Company",
        "title": "Someone used Claude to build a potential bioweapon. The real threat is much deeper",
        "url": "https://urgent.news/2026/09/19/someone-used-claude-to-build-a-potential-bioweapon-the-real-threat-is",
        "published": "2026-09-19T11:00:00.000Z"
      }
    ]
  },
  "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."
}