<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Most recent entries from all</title>
    <link>https://cve.radiocsirt.org</link>
    <description>Contains only the most 10 recent entries.</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>python-feedgen</generator>
    <language>en</language>
    <lastBuildDate>Wed, 07 Oct 2026 05:05:24 +0000</lastBuildDate>
    <item>
      <title>EUVD-2026-329636</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-329636</link>
      <description>EUVD-2026-329636</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-329636</guid>
    </item>
    <item>
      <title>fkie_cve-2026-54316</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2026-54316</link>
      <description>&lt;p&gt;Claude Code is an agentic coding tool.  From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 2.1.163.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;Claude Code is an agentic coding tool.  From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 2.1.163.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2026-54316</guid>
    </item>
    <item>
      <title>GHSA-fg94-h982-f3mm — Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-fg94-h982-f3mm</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: @anthropic-ai/claude-code&lt;/p&gt;
&lt;p&gt;Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version.&lt;/p&gt;
&lt;p&gt;Thank you to hackerone.com/novee for reporting this issue.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: @anthropic-ai/claude-code&lt;/p&gt;
&lt;p&gt;Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version.&lt;/p&gt;
&lt;p&gt;Thank you to hackerone.com/novee for reporting this issue.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-fg94-h982-f3mm</guid>
    </item>
  </channel>
</rss>
