{"version":"1.0","type":"rich","provider_name":"gaks.ai AI Glossary","provider_url":"https://gaks.ai/glossary","title":"Data Exfiltration Through Context — 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;\">Data Exfiltration Through Context</h3><p style=\"margin:0 0 12px;font-size:14px;line-height:1.6;\">A form of Data Exfiltration where an attacker uses Indirect Prompt Injection embedded in retrieved content or tool output to trick an LLM agent into leaking sensitive context, credentials or prior conversation data, made more practical as agents gain browsing and tool-calling capabilities.</p><a href=\"https://gaks.ai/glossary/data-exfiltration-through-context\" style=\"font-size:12px;color:#0077aa;\">Source: gaks.ai/glossary/data-exfiltration-through-context →</a></div>"}