{"version":"1.0","type":"rich","provider_name":"gaks.ai AI Glossary","provider_url":"https://gaks.ai/glossary","title":"Lethal Trifecta — AI Glossary","author_name":"Glenn Katrud Solheim","author_url":"https://gaks.ai","width":600,"height":200,"html":"<div style=\"font-family:sans-serif;border:1px solid #e0e0e0;border-radius:8px;padding:16px;max-width:600px;background:#ffffff;color:#111111;\"><p style=\"margin:0 0 4px;font-size:11px;color:#666;\">AI Glossary — gaks.ai</p><h3 style=\"margin:0 0 8px;font-size:16px;\">Lethal Trifecta</h3><p style=\"margin:0 0 12px;font-size:14px;line-height:1.6;\">A framework, coined by researcher [Simon Willison](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/), describing the combination of three properties that makes an AI agent dangerous: access to private data, exposure to untrusted content, and the ability to communicate externally. When all three are present at once, an attacker can use prompt injection to exfiltrate the private data.</p><a href=\"https://gaks.ai/glossary/lethal-trifecta\" style=\"font-size:12px;color:#0077aa;\">Source: gaks.ai/glossary/lethal-trifecta →</a></div>"}