<?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://db.gcve.eu</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, 31 Oct 2026 02:08:32 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-115917 — vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server</title>
      <link>https://db.gcve.eu/vuln/cve-2026-115917</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; vllm-project vllm&lt;/p&gt;
&lt;p&gt;vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim&amp;#39;s browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. 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; vllm-project vllm&lt;/p&gt;
&lt;p&gt;vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim&amp;#39;s browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://db.gcve.eu/vuln/cve-2026-115917</guid>
    </item>
    <item>
      <title>GHSA-vvpg-rrww-wpmh — vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server</title>
      <link>https://db.gcve.eu/vuln/ghsa-vvpg-rrww-wpmh</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;The OpenAI-compatible server registers Starlette `CORSMiddleware` with
`allowed_origins` defaulting to `[&amp;#34;*&amp;#34;]`, and performs no authentication unless
`--api-key` (or `VLLM_API_KEY`) is configured. A web page on any origin can send
requests to a vLLM server that the victim&amp;#39;s browser can reach (for example
`localhost` or an internal/VPN address) and read the responses. The default
`allow_credentials=False` blocks cookie-bearing cross-origin requests; because
vLLM authenticates with a bearer header rather than cookies, the wildcard still
permits untokenized access to an unauthenticated server and read access when the
caller already holds a token.&lt;/p&gt;
&lt;p&gt;### Details&lt;/p&gt;
&lt;p&gt;Affected components&lt;/p&gt;
&lt;p&gt;- `vllm/entrypoints/launchers/cli_args.py` - `allowed_origins` default value.
- `vllm/entrypoints/serve/middleware/register.py` - `CORSMiddleware`
  registration.
- `vllm/entrypoints/serve/middleware/authenticate.py` - auth middleware and its
  guarded path prefixes.&lt;/p&gt;
&lt;p&gt;Root cause&lt;/p&gt;
&lt;p&gt;`vllm/entrypoints/launchers/cli_args.py`:&lt;/p&gt;
&lt;p&gt;```python
allow_credentials: bool = False
&amp;#34;&amp;#34;&amp;#34;Allow credentials.&amp;#34;&amp;#34;&amp;#34;
allowed_origins: list[str] = field(default_factory=lambda: [&amp;#34;*&amp;#34;])
&amp;#34;&amp;#34;&amp;#34;Allowed origins.&amp;#34;&amp;#34;&amp;#34;
```&lt;/p&gt;
&lt;p&gt;`vllm/entrypoints/serve/middleware/register.py`:&lt;/p&gt;
&lt;p&gt;```python
app.add_middleware(
    CORSMiddleware,
    allow_origins=args.allowed_origins,
    allow_credentials=args.allow_credentials,
    allow_methods=args.allowed_methods,
    allow_headers=args.allowed_headers,
)
```&lt;/p&gt;
&lt;p&gt;The auth middleware is added only when a…&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;The OpenAI-compatible server registers Starlette `CORSMiddleware` with
`allowed_origins` defaulting to `[&amp;#34;*&amp;#34;]`, and performs no authentication unless
`--api-key` (or `VLLM_API_KEY`) is configured. A web page on any origin can send
requests to a vLLM server that the victim&amp;#39;s browser can reach (for example
`localhost` or an internal/VPN address) and read the responses. The default
`allow_credentials=False` blocks cookie-bearing cross-origin requests; because
vLLM authenticates with a bearer header rather than cookies, the wildcard still
permits untokenized access to an unauthenticated server and read access when the
caller already holds a token.&lt;/p&gt;
&lt;p&gt;### Details&lt;/p&gt;
&lt;p&gt;Affected components&lt;/p&gt;
&lt;p&gt;- `vllm/entrypoints/launchers/cli_args.py` - `allowed_origins` default value.
- `vllm/entrypoints/serve/middleware/register.py` - `CORSMiddleware`
  registration.
- `vllm/entrypoints/serve/middleware/authenticate.py` - auth middleware and its
  guarded path prefixes.&lt;/p&gt;
&lt;p&gt;Root cause&lt;/p&gt;
&lt;p&gt;`vllm/entrypoints/launchers/cli_args.py`:&lt;/p&gt;
&lt;p&gt;```python
allow_credentials: bool = False
&amp;#34;&amp;#34;&amp;#34;Allow credentials.&amp;#34;&amp;#34;&amp;#34;
allowed_origins: list[str] = field(default_factory=lambda: [&amp;#34;*&amp;#34;])
&amp;#34;&amp;#34;&amp;#34;Allowed origins.&amp;#34;&amp;#34;&amp;#34;
```&lt;/p&gt;
&lt;p&gt;`vllm/entrypoints/serve/middleware/register.py`:&lt;/p&gt;
&lt;p&gt;```python
app.add_middleware(
    CORSMiddleware,
    allow_origins=args.allowed_origins,
    allow_credentials=args.allow_credentials,
    allow_methods=args.allowed_methods,
    allow_headers=args.allowed_headers,
)
```&lt;/p&gt;
&lt;p&gt;The auth middleware is added only when a…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://db.gcve.eu/vuln/ghsa-vvpg-rrww-wpmh</guid>
    </item>
  </channel>
</rss>
