<?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>2026-09-30T11:37:36.439467+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-2026-56696</id>
    <title>CVE-2026-56696 — OpenHarness - Prompt Injection via /issue and /pr_comments Slash Commands</title>
    <updated>2026-09-30T11:37:36.441563+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> HKUDS OpenHarness</p>
<p>OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/pr_comments.md files, which are subsequently injected into runtime system prompts, persistently influencing local agent behavior.</p></div>
    </content>
    <link href="https://db.gcve.eu/vuln/cve-2026-56696"/>
  </entry>
  <entry>
    <id>https://db.gcve.eu/vuln/pysec-2026-3880</id>
    <title>PYSEC-2026-3880 — OpenHarness remote project-context commands allow persistent prompt poisoning</title>
    <updated>2026-09-30T11:37:36.441676+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> PyPI: openharness-ai</p>
<p>OpenHarness /issue and /pr_comments slash commands lack remote_invocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/pr_comments.md files, which are subsequently injected into runtime system prompts, persistently influencing local agent behavior.</p></div>
    </content>
    <link href="https://db.gcve.eu/vuln/pysec-2026-3880"/>
  </entry>
</feed>
