<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Robotics on CuraSec</title><link>https://curasec.metacog.co.kr/tags/robotics/</link><description>Recent content in Robotics on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 26 Oct 2026 18:39:19 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/robotics/index.xml" rel="self" type="application/rss+xml"/><item><title>Goal Insertion Attacks Bypass Humanoid Robot Safety Filters</title><link>https://curasec.metacog.co.kr/insights/2026-10-26-not-an-accident-exploiting-safety-filter-inadequacy-in-human/</link><pubDate>Mon, 26 Oct 2026 18:39:19 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-10-26-not-an-accident-exploiting-safety-filter-inadequacy-in-human/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Learn:&lt;/strong> Novel attack class showing that safety-filter guarantees in humanoid robots break when deployment parameters differ from configuration assumptions — relevant if your org is evaluating or deploying robotics platforms, but no patch or configuration action exists yet.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Leader — Learn:&lt;/strong> Emerging risk category: researchers demonstrate that safety guarantees in commercially deployed humanoid robots can be defeated through normal user interactions; worth tracking if your organization operates or plans to deploy robotics in warehouses or clinical environments.&lt;/li>
&lt;/ul></description></item></channel></rss>