<?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>CVE-2026 on Judy AI Lab</title>
    <link>https://judyailab.com/en/tags/cve-2026/</link>
    <description>Recent content in CVE-2026 on Judy AI Lab</description>
    <image>
      <title>Judy AI Lab</title>
      <url>https://judyailab.com/logo.jpg</url>
      <link>https://judyailab.com/logo.jpg</link>
    </image>
    <generator>Hugo -- 0.147.4</generator>
    <language>en</language>
    <lastBuildDate>Tue, 07 Apr 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://judyailab.com/en/tags/cve-2026/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>360 Uncovers Three Critical Vulnerabilities in OpenClaw: Is Your AI Agent Safe in the Agent Era?</title>
      <link>https://judyailab.com/en/posts/openclaw-360-vulnerabilities-ai-agent-security/</link>
      <pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://judyailab.com/en/posts/openclaw-360-vulnerabilities-ai-agent-security/</guid>
      <description>360security team exposes three high-risk vulnerabilities in OpenClaw, with CVSS scores up to 8.1. MEDIA protocol Prompt injection can bypass all tool permissions to steal sensitive server data, and over 340 malicious plugins on ClawHub pose a supply chain threat. Essential security guide for enterprises deploying AI Agents.</description>
    </item>
  </channel>
</rss>
