<?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, 16 Nov 2026 21:00:55 +0000</lastBuildDate>
    <item>
      <title>EUVD-2026-396348</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-396348</link>
      <description>EUVD-2026-396348</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-396348</guid>
    </item>
    <item>
      <title>fkie_cve-2026-115918</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2026-115918</link>
      <description>&lt;p&gt;vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2026-115918</guid>
    </item>
    <item>
      <title>GHSA-x567-49g5-p4cf — vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-x567-49g5-p4cf</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;vLLM&amp;#39;s `/v1/responses` endpoint accepts request-level `chat_template_kwargs`, but does not apply the `--trust-request-chat-template` gate that protects Chat Completions, render, tokenize, and pooling paths.&lt;/p&gt;
&lt;p&gt;When the server is run with the documented default `trust_request_chat_template=False` and no explicit `--chat-template`, a Responses request can pass:&lt;/p&gt;
&lt;p&gt;```json
{&amp;#34;chat_template_kwargs&amp;#34;: {&amp;#34;chat_template&amp;#34;: &amp;#34;&amp;lt;attacker Jinja template&amp;gt;&amp;#34;}}
```&lt;/p&gt;
&lt;p&gt;That key is preserved by `ChatParams.get_apply_chat_template_kwargs()` and then bound as the `chat_template` parameter to the shared HF renderer. Prior vLLM advisories establish that request-controlled Jinja chat templates can cause CPU/memory exhaustion. This report covers the current-head Responses sibling path missed by the earlier fixes.&lt;/p&gt;
&lt;p&gt;## Technical Details&lt;/p&gt;
&lt;p&gt;The shared OpenAI frontend has a validation helper that rejects request-supplied chat templates unless the trust flag is enabled. It explicitly checks both top-level `chat_template` and `chat_template_kwargs[&amp;#34;chat_template&amp;#34;]`.&lt;/p&gt;
&lt;p&gt;Responses is a separate serving path:&lt;/p&gt;
&lt;p&gt;- `vllm/entrypoints/openai/responses/protocol.py` exposes `chat_template_kwargs`.
- `ResponsesRequest.build_chat_params()` merges request kwargs.
- `OpenAIServingResponses._effective_chat_template_kwargs()` uses those kwargs.
- `ChatParams.get_apply_chat_template_kwargs()` preserves a request `chat_template` key when the server chat template is `None`.
- `vllm/renderers/hf.py` unpacks the result into `s…&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;vLLM&amp;#39;s `/v1/responses` endpoint accepts request-level `chat_template_kwargs`, but does not apply the `--trust-request-chat-template` gate that protects Chat Completions, render, tokenize, and pooling paths.&lt;/p&gt;
&lt;p&gt;When the server is run with the documented default `trust_request_chat_template=False` and no explicit `--chat-template`, a Responses request can pass:&lt;/p&gt;
&lt;p&gt;```json
{&amp;#34;chat_template_kwargs&amp;#34;: {&amp;#34;chat_template&amp;#34;: &amp;#34;&amp;lt;attacker Jinja template&amp;gt;&amp;#34;}}
```&lt;/p&gt;
&lt;p&gt;That key is preserved by `ChatParams.get_apply_chat_template_kwargs()` and then bound as the `chat_template` parameter to the shared HF renderer. Prior vLLM advisories establish that request-controlled Jinja chat templates can cause CPU/memory exhaustion. This report covers the current-head Responses sibling path missed by the earlier fixes.&lt;/p&gt;
&lt;p&gt;## Technical Details&lt;/p&gt;
&lt;p&gt;The shared OpenAI frontend has a validation helper that rejects request-supplied chat templates unless the trust flag is enabled. It explicitly checks both top-level `chat_template` and `chat_template_kwargs[&amp;#34;chat_template&amp;#34;]`.&lt;/p&gt;
&lt;p&gt;Responses is a separate serving path:&lt;/p&gt;
&lt;p&gt;- `vllm/entrypoints/openai/responses/protocol.py` exposes `chat_template_kwargs`.
- `ResponsesRequest.build_chat_params()` merges request kwargs.
- `OpenAIServingResponses._effective_chat_template_kwargs()` uses those kwargs.
- `ChatParams.get_apply_chat_template_kwargs()` preserves a request `chat_template` key when the server chat template is `None`.
- `vllm/renderers/hf.py` unpacks the result into `s…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-x567-49g5-p4cf</guid>
    </item>
    <item>
      <title>PYSEC-2026-4349</title>
      <link>https://cve.radiocsirt.org/vuln/pysec-2026-4349</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/pysec-2026-4349</guid>
    </item>
    <item>
      <title>WID-SEC-W-2026-4051 — vllm: Mehrere Schwachstellen</title>
      <link>https://cve.radiocsirt.org/vuln/wid-sec-w-2026-4051</link>
      <description>&lt;p&gt;Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um beliebigen Programmcode auszuführen, um einen Denial of Service Angriff durchzuführen, um Informationen offenzulegen und um Sicherheitsvorkehrungen zu umgehen.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um beliebigen Programmcode auszuführen, um einen Denial of Service Angriff durchzuführen, um Informationen offenzulegen und um Sicherheitsvorkehrungen zu umgehen.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/wid-sec-w-2026-4051</guid>
    </item>
  </channel>
</rss>
