<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://cve.radiocsirt.org/rss/recent/all/10</id>
  <title>Most recent entries from all</title>
  <updated>2026-10-06T01:05:52.260747+00:00</updated>
  <author>
    <name>Vulnerability-Lookup</name>
    <email>csirt@opendfir.org</email>
  </author>
  <link href="https://cve.radiocsirt.org" rel="alternate"/>
  <generator uri="https://lkiesow.github.io/python-feedgen" version="1.0.0">python-feedgen</generator>
  <subtitle>Contains only the most 10 recent entries.</subtitle>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/euvd-2026-336203</id>
    <title>EUVD-2026-336203</title>
    <updated>2026-10-06T01:05:52.309212+00:00</updated>
    <content>EUVD-2026-336203</content>
    <link href="https://cve.radiocsirt.org/vuln/euvd-2026-336203"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/fkie_cve-2026-60086</id>
    <title>fkie_cve-2026-60086</title>
    <updated>2026-10-06T01:05:52.309266+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.</p>
      </div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/fkie_cve-2026-60086"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/ghsa-5c3v-h6hw-4gx7</id>
    <title>GHSA-5c3v-h6hw-4gx7</title>
    <updated>2026-10-06T01:05:52.309302+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.</p>
      </div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/ghsa-5c3v-h6hw-4gx7"/>
  </entry>
</feed>
