<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Security on ShaSec</title><link>https://shasec.my.id/en/categories/ai-security/</link><description>Recent content in AI Security on ShaSec</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 28 Jul 2026 08:20:49 +0700</lastBuildDate><atom:link href="https://shasec.my.id/en/categories/ai-security/index.xml" rel="self" type="application/rss+xml"/><item><title>Vishing and AI Voice Cloning: When a Familiar Voice Is Not the Person</title><link>https://shasec.my.id/en/articles/vishing-ai-voice-cloning/</link><pubDate>Fri, 24 Jul 2026 00:00:00 +0000</pubDate><guid>https://shasec.my.id/en/articles/vishing-ai-voice-cloning/</guid><description>Scammers now imitate your child, your boss, or a bank officer using AI trained on a few seconds of audio. Learn how it works, the signs you can still catch, and the verification habits that stop it.</description></item><item><title>Prompt Injection and AI Agent Security: Protecting Data and Automated Actions</title><link>https://shasec.my.id/en/articles/prompt-injection-ai-agent/</link><pubDate>Sat, 04 Jul 2026 00:00:00 +0000</pubDate><guid>https://shasec.my.id/en/articles/prompt-injection-ai-agent/</guid><description>AI agents can read data and run tools. Understand prompt injection, limit permissions, and require human review so automation does not become a data-leak path.</description></item><item><title>How to Use AI at Work Without Leaking Data</title><link>https://shasec.my.id/en/articles/shadow-ai-security/</link><pubDate>Wed, 01 Jul 2026 00:00:00 +0000</pubDate><guid>https://shasec.my.id/en/articles/shadow-ai-security/</guid><description>AI can speed up work, but unmanaged tools can move sensitive data to places you do not control. Build practical habits and rules.</description></item></channel></rss>