<?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>Fri, 02 Oct 2026 18:35:10 +0000</lastBuildDate>
    <item>
      <title>BREW-aider-CVE-2026-42271 — LiteLLM: Authenticated command execution via MCP stdio test endpoints</title>
      <link>https://cve.radiocsirt.org/vuln/brew-aider-cve-2026-42271</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; Homebrew: aider&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;Two endpoints used to preview an MCP server before saving it — `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` — accepted a full server configuration in the request body, including the `command`, `args`, and `env` fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process.&lt;/p&gt;
&lt;p&gt;The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host.&lt;/p&gt;
&lt;p&gt;### Patches&lt;/p&gt;
&lt;p&gt;Fixed in **`1.83.7`**. Both test endpoints now require the `PROXY_ADMIN` role, bringing them into line with the save endpoint.&lt;/p&gt;
&lt;p&gt;### Workarounds&lt;/p&gt;
&lt;p&gt;If upgrading is not immediately possible, developers should block `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` at their reverse proxy or API gateway.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; Homebrew: aider&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;Two endpoints used to preview an MCP server before saving it — `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` — accepted a full server configuration in the request body, including the `command`, `args`, and `env` fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process.&lt;/p&gt;
&lt;p&gt;The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host.&lt;/p&gt;
&lt;p&gt;### Patches&lt;/p&gt;
&lt;p&gt;Fixed in **`1.83.7`**. Both test endpoints now require the `PROXY_ADMIN` role, bringing them into line with the save endpoint.&lt;/p&gt;
&lt;p&gt;### Workarounds&lt;/p&gt;
&lt;p&gt;If upgrading is not immediately possible, developers should block `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` at their reverse proxy or API gateway.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/brew-aider-cve-2026-42271</guid>
    </item>
    <item>
      <title>EUVD-2026-337244</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-337244</link>
      <description>EUVD-2026-337244</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-337244</guid>
    </item>
    <item>
      <title>fkie_cve-2026-42271</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2026-42271</link>
      <description>&lt;p&gt;LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2026-42271</guid>
    </item>
    <item>
      <title>GHSA-v4p8-mg3p-g94g — LiteLLM: Authenticated command execution via MCP stdio test endpoints</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-v4p8-mg3p-g94g</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;Two endpoints used to preview an MCP server before saving it — `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` — accepted a full server configuration in the request body, including the `command`, `args`, and `env` fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process.&lt;/p&gt;
&lt;p&gt;The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host.&lt;/p&gt;
&lt;p&gt;### Patches&lt;/p&gt;
&lt;p&gt;Fixed in **`1.83.7`**. Both test endpoints now require the `PROXY_ADMIN` role, bringing them into line with the save endpoint.&lt;/p&gt;
&lt;p&gt;### Workarounds&lt;/p&gt;
&lt;p&gt;If upgrading is not immediately possible, developers should block `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` at their reverse proxy or API gateway.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;Two endpoints used to preview an MCP server before saving it — `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` — accepted a full server configuration in the request body, including the `command`, `args`, and `env` fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process.&lt;/p&gt;
&lt;p&gt;The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host.&lt;/p&gt;
&lt;p&gt;### Patches&lt;/p&gt;
&lt;p&gt;Fixed in **`1.83.7`**. Both test endpoints now require the `PROXY_ADMIN` role, bringing them into line with the save endpoint.&lt;/p&gt;
&lt;p&gt;### Workarounds&lt;/p&gt;
&lt;p&gt;If upgrading is not immediately possible, developers should block `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` at their reverse proxy or API gateway.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-v4p8-mg3p-g94g</guid>
    </item>
    <item>
      <title>NCSC-2026-0137 — Kwetsbaarheden verholpen in LiteLLM door BerriAI</title>
      <link>https://cve.radiocsirt.org/vuln/ncsc-2026-0137</link>
      <description>NCSC-2026-0137</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ncsc-2026-0137</guid>
    </item>
    <item>
      <title>PYSEC-2026-2599 — LiteLLM: Authenticated command execution via MCP stdio test endpoints</title>
      <link>https://cve.radiocsirt.org/vuln/pysec-2026-2599</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;Two endpoints used to preview an MCP server before saving it — `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` — accepted a full server configuration in the request body, including the `command`, `args`, and `env` fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process.&lt;/p&gt;
&lt;p&gt;The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host.&lt;/p&gt;
&lt;p&gt;### Patches&lt;/p&gt;
&lt;p&gt;Fixed in **`1.83.7`**. Both test endpoints now require the `PROXY_ADMIN` role, bringing them into line with the save endpoint.&lt;/p&gt;
&lt;p&gt;### Workarounds&lt;/p&gt;
&lt;p&gt;If upgrading is not immediately possible, developers should block `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` at their reverse proxy or API gateway.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;### Impact&lt;/p&gt;
&lt;p&gt;Two endpoints used to preview an MCP server before saving it — `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` — accepted a full server configuration in the request body, including the `command`, `args`, and `env` fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process.&lt;/p&gt;
&lt;p&gt;The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host.&lt;/p&gt;
&lt;p&gt;### Patches&lt;/p&gt;
&lt;p&gt;Fixed in **`1.83.7`**. Both test endpoints now require the `PROXY_ADMIN` role, bringing them into line with the save endpoint.&lt;/p&gt;
&lt;p&gt;### Workarounds&lt;/p&gt;
&lt;p&gt;If upgrading is not immediately possible, developers should block `POST /mcp-rest/test/connection` and `POST /mcp-rest/test/tools/list` at their reverse proxy or API gateway.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/pysec-2026-2599</guid>
    </item>
    <item>
      <title>RHSA-2026:27784 — Red Hat Security Advisory: RHOAI 3.4.1 - Red Hat OpenShift AI</title>
      <link>https://cve.radiocsirt.org/vuln/rhsa-2026:27784</link>
      <description>&lt;p&gt;litellm: LiteLLM: Authenticated command execution via MCP stdio test endpoints&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;litellm: LiteLLM: Authenticated command execution via MCP stdio test endpoints&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/rhsa-2026:27784</guid>
    </item>
    <item>
      <title>WID-SEC-W-2026-1288 — LiteLLM: Mehrere Schwachstellen</title>
      <link>https://cve.radiocsirt.org/vuln/wid-sec-w-2026-1288</link>
      <description>&lt;p&gt;Ein Angreifer kann mehrere Schwachstellen in LiteLLM ausnutzen, um einen SQL-Injection-Angriff durchzuführen und sich unbefugten Zugriff zu verschaffen oder um beliebigen Programmcode mit den Rechten des Dienstes auszuführen&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;Ein Angreifer kann mehrere Schwachstellen in LiteLLM ausnutzen, um einen SQL-Injection-Angriff durchzuführen und sich unbefugten Zugriff zu verschaffen oder um beliebigen Programmcode mit den Rechten des Dienstes auszuführen&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/wid-sec-w-2026-1288</guid>
    </item>
  </channel>
</rss>
