<?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://vulnerability.circl.lu/rss/recent/all/10</id>
  <title>Most recent entries from all</title>
  <updated>2026-10-08T17:24:31.966039+00:00</updated>
  <author>
    <name>Vulnerability-Lookup</name>
    <email>info@circl.lu</email>
  </author>
  <link href="https://vulnerability.circl.lu" 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://vulnerability.circl.lu/vuln/cve-2026-107183</id>
    <title>CVE-2026-107183 — llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parser</title>
    <updated>2026-10-08T17:24:32.434882+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> ggml-org llama.cpp</p>
<p>llama.cpp before b11393 contains a use-after-free and double free vulnerability in common_chat_peg_mapper::map that allows unauthenticated remote attackers to corrupt heap memory via a dangling current_tool pointer. Attackers can submit a chat_parser in a POST /completion request emitting a tool-id after a tool-close tag to crash llama-server and shape a heap write primitive.</p></div>
    </content>
    <link href="https://vulnerability.circl.lu/vuln/cve-2026-107183"/>
  </entry>
</feed>
