<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Memory Poisoning on Vivian@SecMomBag</title><link>https://vvnblog.com/en/tags/memory-poisoning/</link><description>Recent content in Memory Poisoning on Vivian@SecMomBag</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>Copyright © 2026 Vivian All Rights Reserved.</copyright><lastBuildDate>Sun, 16 Aug 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://vvnblog.com/en/tags/memory-poisoning/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Dark Arts (15): When the AI Acts on Its Own, Taking Apart the Moment an Agent Falls</title><link>https://vvnblog.com/en/posts/ai-dark-arts-15/</link><pubDate>Sun, 16 Aug 2026 00:00:00 +0800</pubDate><guid>https://vvnblog.com/en/posts/ai-dark-arts-15/</guid><description>Once an AI has tools, memory and an autonomous loop, a mistake no longer stops at the answer. A tool argument, a sentence in memory, a text file in the project: an agent can promote any of them into an instruction it treats as approved.</description></item></channel></rss>