<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>C2 on Aleph Beth</title>
    <link>https://www.alephbeth.ai/tags/c2/</link>
    <description>Recent content in C2 on Aleph Beth</description>
    <image>
      <title>Aleph Beth</title>
      <url>https://www.alephbeth.ai/og-image.jpg</url>
      <link>https://www.alephbeth.ai/og-image.jpg</link>
    </image>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Sun, 13 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://www.alephbeth.ai/tags/c2/rss.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The Hidden Weapon in the Page</title>
      <link>https://www.alephbeth.ai/posts/2026-09-13-hidden-weapon-in-the-page/</link>
      <pubDate>Sun, 13 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://www.alephbeth.ai/posts/2026-09-13-hidden-weapon-in-the-page/</guid>
      <description>An indexed web page can carry a natural-language payload that targets, in a few lines, all four defensive layers of an AI agent: evasion, persistence, exfiltration, concealment. Worse, the outbound channel used for exfiltration is bidirectional: behind the URL, an attacker talks to the agent in real time. This article details the mechanism, shows why warning the model is a necessary but never sufficient first line, and why security comes from architecture — not from the prompt.</description>
    </item>
  </channel>
</rss>
