<?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://db.gcve.eu/rss/recent/all/10</id>
  <title>Most recent entries from all</title>
  <updated>2026-11-21T04:57:56.975636+00:00</updated>
  <author>
    <name>Vulnerability-Lookup</name>
    <email>info@gcve.eu</email>
  </author>
  <link href="https://db.gcve.eu" 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://db.gcve.eu/vuln/cve-2026-130686</id>
    <title>CVE-2026-130686 — vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image Requests</title>
    <updated>2026-11-21T04:57:56.977311+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> vllm-project vllm</p>
<p>vLLM from 0.6.0 before 0.33.0 lacks a request-wide media budget, allowing remote inference clients to exhaust frontend resources by submitting many remote image URLs in one request. Attackers can send a compact request to /v1/messages or /v1/responses that forces downloading and decoding of every image before prompt-length admission, exhausting memory, CPU, and connections.</p></div>
    </content>
    <link href="https://db.gcve.eu/vuln/cve-2026-130686"/>
  </entry>
</feed>
