<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Tools on CuraSec</title><link>https://curasec.metacog.co.kr/tags/ai-tools/</link><description>Recent content in Ai-Tools on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 15 Jul 2026 12:11:39 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/ai-tools/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude for Chrome Flaw Lets Rogue Extensions Access Gmail, Docs, Calendar</title><link>https://curasec.metacog.co.kr/insights/2026-07-15-researchers-say-claude-for-chrome-flaw-lets-rogue-extensions/</link><pubDate>Wed, 15 Jul 2026 12:11:39 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-07-15-researchers-say-claude-for-chrome-flaw-lets-rogue-extensions/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Plan:&lt;/strong> If Claude for Chrome is deployed in your environment, audit which other extensions have scripting access to claude.ai and consider disabling the integration until Anthropic ships a complete fix; Anthropic&amp;rsquo;s May patch only narrowed the arbitrary-prompt path, not the cross-extension trigger surface.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Learn:&lt;/strong> The attack chain (rogue extension injecting scripts on claude.ai to pivot into Gmail/Docs/Calendar) represents a new cross-extension privilege escalation pattern via AI browser tools; no active exploitation or IOCs reported, so no hunt to run today, but worth modeling for detection of unauthorized extension installs.&lt;/li>
&lt;li>&lt;strong>Leader — Plan:&lt;/strong> If Claude for Chrome is in your approved-tools list, confirm with your IT/security team whether employees are running it and assess exposure to sensitive data in Gmail, Docs, and Calendar; request Anthropic&amp;rsquo;s remediation timeline before the next quarterly tool review.&lt;/li>
&lt;/ul></description></item></channel></rss>