<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Sdk-Vulnerability on CuraSec</title><link>https://curasec.metacog.co.kr/tags/sdk-vulnerability/</link><description>Recent content in Sdk-Vulnerability on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 23 Oct 2026 15:44:28 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/sdk-vulnerability/index.xml" rel="self" type="application/rss+xml"/><item><title>x402 SDK Default Client Allowed Malicious APIs to Drain AI Agent Wallets</title><link>https://curasec.metacog.co.kr/insights/2026-10-23-critical-x402-sdk-flaw-could-let-malicious-apis-drain-ai-age/</link><pubDate>Fri, 23 Oct 2026 15:44:28 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-10-23-critical-x402-sdk-flaw-could-let-malicious-apis-drain-ai-age/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Plan:&lt;/strong> Teams running x402-enabled AI agents with automatic payment signing are exposed if they haven&amp;rsquo;t upgraded to the August 18 release; update the x402 SDK and add explicit per-request spending limits in agent configuration.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Leader — Learn:&lt;/strong> This flaw illustrates why AI agent deployments need explicit financial guardrails as a governance control; useful context when drafting AI agent usage policies before broader enterprise rollout.&lt;/li>
&lt;/ul></description></item></channel></rss>