<?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 12:09:58 +0000</lastBuildDate>
    <item>
      <title>BREW-rawdog-CVE-2024-2952 — LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint</title>
      <link>https://cve.radiocsirt.org/vuln/brew-rawdog-cve-2024-2952</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; Homebrew: rawdog&lt;/p&gt;
&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; Homebrew: rawdog&lt;/p&gt;
&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/brew-rawdog-cve-2024-2952</guid>
    </item>
    <item>
      <title>EUVD-2026-2066</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-2066</link>
      <description>EUVD-2026-2066</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-2066</guid>
    </item>
    <item>
      <title>fkie_cve-2024-2952</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2024-2952</link>
      <description>&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2024-2952</guid>
    </item>
    <item>
      <title>GHSA-46cm-pfwv-cgf8 — LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-46cm-pfwv-cgf8</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-46cm-pfwv-cgf8</guid>
    </item>
    <item>
      <title>gsd-2024-2952</title>
      <link>https://cve.radiocsirt.org/vuln/gsd-2024-2952</link>
      <description>gsd-2024-2952</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/gsd-2024-2952</guid>
    </item>
    <item>
      <title>PYSEC-2026-387 — LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint</title>
      <link>https://cve.radiocsirt.org/vuln/pysec-2026-387</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: litellm&lt;/p&gt;
&lt;p&gt;BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/pysec-2026-387</guid>
    </item>
  </channel>
</rss>
