<?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>Mon, 19 Oct 2026 02:52:24 +0000</lastBuildDate>
    <item>
      <title>EUVD-2026-266478</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-266478</link>
      <description>EUVD-2026-266478</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-266478</guid>
    </item>
    <item>
      <title>fkie_cve-2026-0755</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2026-0755</link>
      <description>&lt;p&gt;gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of gemini-mcp-tool. Authentication is not required to exploit this vulnerability.&lt;/p&gt;
&lt;p&gt;The specific flaw exists within the implementation of the execAsync method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27783.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of gemini-mcp-tool. Authentication is not required to exploit this vulnerability.&lt;/p&gt;
&lt;p&gt;The specific flaw exists within the implementation of the execAsync method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27783.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2026-0755</guid>
    </item>
    <item>
      <title>GHSA-4h5r-5jm8-jxjm — gemini-mcp-tool vulnerable to OS command injection and @file exfiltration via prompt quoting (CVE-2026-0755)</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-4h5r-5jm8-jxjm</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: gemini-mcp-tool&lt;/p&gt;
&lt;p&gt;Untrusted prompt input could reach the Gemini CLI @file parser, allowing read/exfiltration of arbitrary local files (@/etc/passwd, @~/.ssh/id_rsa, @../../secret). On Windows, unquoted cmd.exe metacharacters could break out into OS command injection.&lt;/p&gt;
&lt;p&gt;Fix (1.1.6): removed the broken shell:false double-quote wrapping; added assertSafeFileReferences() to contain @file refs to the working directory; hardened Windows cmd.exe argument quoting.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: gemini-mcp-tool&lt;/p&gt;
&lt;p&gt;Untrusted prompt input could reach the Gemini CLI @file parser, allowing read/exfiltration of arbitrary local files (@/etc/passwd, @~/.ssh/id_rsa, @../../secret). On Windows, unquoted cmd.exe metacharacters could break out into OS command injection.&lt;/p&gt;
&lt;p&gt;Fix (1.1.6): removed the broken shell:false double-quote wrapping; added assertSafeFileReferences() to contain @file refs to the working directory; hardened Windows cmd.exe argument quoting.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-4h5r-5jm8-jxjm</guid>
    </item>
  </channel>
</rss>
