<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Microsoft-Copilot on CuraSec</title><link>https://curasec.metacog.co.kr/tags/microsoft-copilot/</link><description>Recent content in Microsoft-Copilot on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 19 Aug 2026 11:36:35 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/microsoft-copilot/index.xml" rel="self" type="application/rss+xml"/><item><title>Microsoft Copilot Personal CoSnitch Flaws Enable One-Click Data Exfiltration</title><link>https://curasec.metacog.co.kr/insights/2026-08-19-microsoft-copilot-personal-flaws-could-let-one-click-exfiltr/</link><pubDate>Wed, 19 Aug 2026 11:36:35 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-08-19-microsoft-copilot-personal-flaws-could-let-one-click-exfiltr/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Learn:&lt;/strong> No enrichment signals and no patch details are provided, but the CoSnitch research illustrates how undocumented AI assistant parameters can become exfiltration channels — worth factoring into security reviews of any AI integrations or OAuth-connected app architectures you own.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Learn:&lt;/strong> No IOCs, no active exploitation, and no detection artifacts are available; the one-click-via-crafted-link technique is worth noting for future phishing-via-AI-assistant scenarios, but there is nothing actionable to hunt or detect today.&lt;/li>
&lt;li>&lt;strong>Leader — Plan:&lt;/strong> Employees who connect corporate accounts or data to personal Microsoft Copilot sessions may be exposed to this exfiltration path — assess whether current acceptable-use or CASB policies cover personal AI assistant tools and extend them if not.&lt;/li>
&lt;/ul></description></item></channel></rss>