{"version":"1.0","type":"rich","provider_name":"techandbusiness.org","provider_url":"https://techandbusiness.org","title":"Report details GPT-6 Astra prompt-injection limits","author_name":"techandbusiness.org · AI, Cybersecurity","thumbnail_url":"https://the-decoder.com/wp-content/uploads/2025/11/openai_logo_wall-3.png","width":600,"height":400,"html":"<blockquote class=\"tb-newswire-embed\" style=\"max-width:600px;border-left:3px solid #22d3ee;padding:12px 16px;margin:0;font-family:-apple-system,system-ui,sans-serif;background:#09090b;border-radius:0 8px 8px 0;\">\n      <p style=\"margin:0 0 8px;font-size:10px;font-weight:600;letter-spacing:0.1em;color:#71717a;\">techandbusiness.org · AI, Cybersecurity</p>\n      <p style=\"margin:0 0 8px;font-size:18px;font-weight:700;line-height:1.3;color:#fff;\"><a href=\"https://techandbusiness.org/newswire/-oKssQP33xKD3ppK_8A_VX\" style=\"color:#fff;text-decoration:none;\">Report details GPT-6 Astra prompt-injection limits</a></p>\n      <p style=\"margin:0;font-size:14px;color:#a1a1aa;line-height:1.5;\">GPT-6 Astra blocked 99.99% of direct prompt-injection attacks in OpenAI testing, according to a report on the model's system card, but persistent multi-round attackers obtained a problematic response ...</p>\n    </blockquote>"}