<?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>Sat, 03 Oct 2026 06:52:07 +0000</lastBuildDate>
    <item>
      <title>EUVD-2026-380519</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-380519</link>
      <description>EUVD-2026-380519</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-380519</guid>
    </item>
    <item>
      <title>fkie_cve-2026-89032</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2026-89032</link>
      <description>&lt;p&gt;BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants&amp;#39; cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants&amp;#39; personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants&amp;#39; cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants&amp;#39; personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2026-89032</guid>
    </item>
    <item>
      <title>GHSA-237m-2qxv-ww7c</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-237m-2qxv-ww7c</link>
      <description>&lt;p&gt;BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants&amp;#39; cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants&amp;#39; personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants&amp;#39; cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants&amp;#39; personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-237m-2qxv-ww7c</guid>
    </item>
    <item>
      <title>openSUSE-SU-2026:11927-1 — python313-litellm-1.103.0-1.1 on GA media</title>
      <link>https://cve.radiocsirt.org/vuln/opensuse-su-2026:11927-1</link>
      <description>&lt;p&gt;python313-litellm-1.103.0-1.1 on GA media&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;python313-litellm-1.103.0-1.1 on GA media&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/opensuse-su-2026:11927-1</guid>
    </item>
    <item>
      <title>WID-SEC-W-2026-3599 — LiteLLM: Schwachstelle ermöglicht Umgehen von Sicherheitsvorkehrungen</title>
      <link>https://cve.radiocsirt.org/vuln/wid-sec-w-2026-3599</link>
      <description>&lt;p&gt;Ein entfernter, authentisierter Angreifer kann eine Schwachstelle in LiteLLM ausnutzen, um Sicherheitsvorkehrungen zu umgehen und so Informationen offenzulegen sowie unbefugte Aktionen durchzuführen.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;Ein entfernter, authentisierter Angreifer kann eine Schwachstelle in LiteLLM ausnutzen, um Sicherheitsvorkehrungen zu umgehen und so Informationen offenzulegen sowie unbefugte Aktionen durchzuführen.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/wid-sec-w-2026-3599</guid>
    </item>
  </channel>
</rss>
