<?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>Sun, 01 Nov 2026 12:19:47 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-60088 — PraisonAI before 4.6.78 Path Traversal via Custom Commands</title>
      <link>https://db.gcve.eu/vuln/cve-2026-60088</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; MervinPraison PraisonAI&lt;/p&gt;
&lt;p&gt;PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outside_secret.txt or absolute paths in project command files to exfiltrate process-readable files into model prompts.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; MervinPraison PraisonAI&lt;/p&gt;
&lt;p&gt;PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outside_secret.txt or absolute paths in project command files to exfiltrate process-readable files into model prompts.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://db.gcve.eu/vuln/cve-2026-60088</guid>
    </item>
    <item>
      <title>PYSEC-2026-4261 — PraisonAI: Project custom command templates can read outside-workspace files into model prompts</title>
      <link>https://db.gcve.eu/vuln/pysec-2026-4261</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: praisonai&lt;/p&gt;
&lt;p&gt;# Project custom command templates can read outside-workspace files into model prompts&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;PraisonAI&amp;#39;s new file-based custom command feature auto-discovers project commands from `.praisonai/commands/*.md`. When a user runs `praisonai run --command &amp;lt;name&amp;gt;` inside a repository, the command body is interpolated before it is sent as the model prompt.&lt;/p&gt;
&lt;p&gt;The interpolation code expands `@path` references by reading files relative to the current working directory, but it does not canonicalize the target or require it to stay inside the project. A repository-controlled command can therefore include `@../outside_secret.txt` or an absolute path and cause PraisonAI to copy process-readable files outside the workspace into the prompt.&lt;/p&gt;
&lt;p&gt;This is a confidentiality issue in the untrusted-repository workflow: a project can make a normal-looking custom command exfiltrate local files to whichever model/provider receives the generated prompt.&lt;/p&gt;
&lt;p&gt;## Technical Details&lt;/p&gt;
&lt;p&gt;The feature was introduced by commit `88cf0c29` (`feat: file-based custom agents and reusable commands with auto-discovery (#2035)`) and is present on current main:&lt;/p&gt;
&lt;p&gt;```text
current commit: 3aa9cbc2bd49c23a32be0a89a5e620d13d843eab
current describe: v4.6.64-8-g3aa9cbc2
```&lt;/p&gt;
&lt;p&gt;`src/praisonai/praisonai/cli/features/custom_definitions.py` discovers project-level definitions by walking upward from `Path.cwd()` to the git root and loading `.praisonai/commands/*.md`. Project commands override user-global commands.&lt;/p&gt;
&lt;p&gt;`interpolate_command…&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: praisonai&lt;/p&gt;
&lt;p&gt;# Project custom command templates can read outside-workspace files into model prompts&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;PraisonAI&amp;#39;s new file-based custom command feature auto-discovers project commands from `.praisonai/commands/*.md`. When a user runs `praisonai run --command &amp;lt;name&amp;gt;` inside a repository, the command body is interpolated before it is sent as the model prompt.&lt;/p&gt;
&lt;p&gt;The interpolation code expands `@path` references by reading files relative to the current working directory, but it does not canonicalize the target or require it to stay inside the project. A repository-controlled command can therefore include `@../outside_secret.txt` or an absolute path and cause PraisonAI to copy process-readable files outside the workspace into the prompt.&lt;/p&gt;
&lt;p&gt;This is a confidentiality issue in the untrusted-repository workflow: a project can make a normal-looking custom command exfiltrate local files to whichever model/provider receives the generated prompt.&lt;/p&gt;
&lt;p&gt;## Technical Details&lt;/p&gt;
&lt;p&gt;The feature was introduced by commit `88cf0c29` (`feat: file-based custom agents and reusable commands with auto-discovery (#2035)`) and is present on current main:&lt;/p&gt;
&lt;p&gt;```text
current commit: 3aa9cbc2bd49c23a32be0a89a5e620d13d843eab
current describe: v4.6.64-8-g3aa9cbc2
```&lt;/p&gt;
&lt;p&gt;`src/praisonai/praisonai/cli/features/custom_definitions.py` discovers project-level definitions by walking upward from `Path.cwd()` to the git root and loading `.praisonai/commands/*.md`. Project commands override user-global commands.&lt;/p&gt;
&lt;p&gt;`interpolate_command…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://db.gcve.eu/vuln/pysec-2026-4261</guid>
    </item>
  </channel>
</rss>
