<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Ai-Vulnerability on ThreatNeuron</title>
    <link>https://thethreatneuron.in/tags/ai-vulnerability/</link>
    <description>Recent content in Ai-Vulnerability on ThreatNeuron</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>© 2026 ThreatNeuron</copyright>
    <lastBuildDate>Sun, 12 Apr 2026 14:23:22 +0530</lastBuildDate><atom:link href="https://thethreatneuron.in/tags/ai-vulnerability/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>GrafanaGhost: Prompt Injection Turns Dashboards Into Spy Tools</title>
      <link>https://thethreatneuron.in/blog/grafanaghost-cve-2026-27876-indirect-prompt-injection-data-exfiltration-2026/</link>
      <pubDate>Sun, 12 Apr 2026 14:23:22 +0530</pubDate>
      
      <guid>https://thethreatneuron.in/blog/grafanaghost-cve-2026-27876-indirect-prompt-injection-data-exfiltration-2026/</guid>
      <description>Noma Security&amp;rsquo;s GrafanaGhost disclosure reveals how indirect prompt injection in Grafana&amp;rsquo;s AI assistant can silently steal financial metrics, infrastructure data, and customer information — without authentication. Here&amp;rsquo;s what happened, how it works, and what to do about it.</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://thethreatneuron.in/blog/grafanaghost-cve-2026-27876-indirect-prompt-injection-data-exfiltration-2026/featured.png" />
    </item>
    
  </channel>
</rss>
