<?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>2026-10-03T14:04:25.772223+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/brew-aider-cve-2026-59822</id>
    <title>BREW-aider-CVE-2026-59822 — LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback</title>
    <updated>2026-10-03T14:04:25.873162+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> Homebrew: aider</p>
<p>### Impact</p>
<p>LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.</p>
<p>The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key validation with an empty `UserAPIKeyAuth()` object. This allowed requests with a fabricated `Authorization` header to reach MCP tooling without a valid LiteLLM key.</p>
<p>An attacker could use this to list and call configured MCP tools and access connected services exposed through MCP.</p>
<p>### Patches</p>
<p>The issue is fixed in `1.84.0`.</p>
<p>We recommend upgrading to `1.84.0` or later.</p>
<p>### Workarounds</p>
<p>If upgrading is not immediately possible, disable MCP routes or block access to `/mcp/` and related MCP endpoints at your reverse proxy or API gateway.</p>
<p>### References</p>
<p>* [v1.84.0](https://github.com/BerriAI/litellm/releases/tag/v1.84.0)</p></div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/brew-aider-cve-2026-59822"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/euvd-2026-363348</id>
    <title>EUVD-2026-363348</title>
    <updated>2026-10-03T14:04:25.873235+00:00</updated>
    <content>EUVD-2026-363348</content>
    <link href="https://cve.radiocsirt.org/vuln/euvd-2026-363348"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/fkie_cve-2026-59822</id>
    <title>fkie_cve-2026-59822</title>
    <updated>2026-10-03T14:04:25.873252+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.84.0, LiteLLM's MCP Streamable HTTP endpoint allowed an unauthenticated attacker to use a fabricated Authorization header to trigger an OAuth2 passthrough fallback path that replaced failed LiteLLM key validation with an empty UserAPIKeyAuth() object, allowing requests to reach MCP tooling without a valid LiteLLM key. This issue is fixed in version 1.84.0.</p>
      </div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/fkie_cve-2026-59822"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/ghsa-7488-6r32-c95q</id>
    <title>GHSA-7488-6r32-c95q — LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback</title>
    <updated>2026-10-03T14:04:25.873277+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> PyPI: litellm</p>
<p>### Impact</p>
<p>LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.</p>
<p>The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key validation with an empty `UserAPIKeyAuth()` object. This allowed requests with a fabricated `Authorization` header to reach MCP tooling without a valid LiteLLM key.</p>
<p>An attacker could use this to list and call configured MCP tools and access connected services exposed through MCP.</p>
<p>### Patches</p>
<p>The issue is fixed in `1.84.0`.</p>
<p>We recommend upgrading to `1.84.0` or later.</p>
<p>### Workarounds</p>
<p>If upgrading is not immediately possible, disable MCP routes or block access to `/mcp/` and related MCP endpoints at your reverse proxy or API gateway.</p>
<p>### References</p>
<p>* [v1.84.0](https://github.com/BerriAI/litellm/releases/tag/v1.84.0)</p></div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/ghsa-7488-6r32-c95q"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/pysec-2026-3479</id>
    <title>PYSEC-2026-3479 — LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback</title>
    <updated>2026-10-03T14:04:25.873308+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> PyPI: litellm</p>
<p>### Impact</p>
<p>LiteLLM's MCP Streamable HTTP endpoint could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.</p>
<p>The MCP auth handler supported OAuth2 passthrough for upstream MCP servers, but the fallback path could replace failed LiteLLM key validation with an empty `UserAPIKeyAuth()` object. This allowed requests with a fabricated `Authorization` header to reach MCP tooling without a valid LiteLLM key.</p>
<p>An attacker could use this to list and call configured MCP tools and access connected services exposed through MCP.</p>
<p>### Patches</p>
<p>The issue is fixed in `1.84.0`.</p>
<p>We recommend upgrading to `1.84.0` or later.</p>
<p>### Workarounds</p>
<p>If upgrading is not immediately possible, disable MCP routes or block access to `/mcp/` and related MCP endpoints at your reverse proxy or API gateway.</p>
<p>### References</p>
<p>* [v1.84.0](https://github.com/BerriAI/litellm/releases/tag/v1.84.0)</p></div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/pysec-2026-3479"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/wid-sec-w-2026-2263</id>
    <title>WID-SEC-W-2026-2263 — LiteLLM: Mehrere Schwachstellen</title>
    <updated>2026-10-03T14:04:25.873337+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>Ein Angreifer kann mehrere Schwachstellen in LiteLLM ausnutzen, um Informationen offenzulegen, Daten zu manipulieren, Code auszuführen und um Sicherheitsmaßnahmen zu umgehen.</p>
      </div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/wid-sec-w-2026-2263"/>
  </entry>
</feed>
