<?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://vulnerability.circl.lu</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>Mon, 28 Sep 2026 11:59:15 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-55522 — PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code</title>
      <link>https://vulnerability.circl.lu/vuln/cve-2026-55522</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; MervinPraison PraisonAI, MervinPraison praisonaiagents&lt;/p&gt;
&lt;p&gt;PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow &amp;#34;include&amp;#34; feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe&amp;#39;s tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; MervinPraison PraisonAI, MervinPraison praisonaiagents&lt;/p&gt;
&lt;p&gt;PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow &amp;#34;include&amp;#34; feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe&amp;#39;s tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://vulnerability.circl.lu/vuln/cve-2026-55522</guid>
    </item>
    <item>
      <title>GHSA-hxmv-c4g6-5fqc — PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code</title>
      <link>https://vulnerability.circl.lu/vuln/ghsa-hxmv-c4g6-5fqc</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: praisonaiagents, PyPI: PraisonAI&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;PraisonAI&amp;#39;s workflow include implementation implicitly imports and executes an included recipe&amp;#39;s `tools.py` file even when the documented `tools.py` autoload opt-in is unset.&lt;/p&gt;
&lt;p&gt;This bypasses the hardening added for the prior automatic `tools.py` RCE advisory family. A workflow that includes an untrusted local recipe can execute arbitrary Python module-level code before any model call or child workflow execution.&lt;/p&gt;
&lt;p&gt;The same sink is reachable through the higher-level `praisonai.recipe.run()` recipe API when a steps-based recipe workflow includes a local child recipe. The supplementary PoV demonstrates this route without starting a network service or relying on external APIs.&lt;/p&gt;
&lt;p&gt;This is distinct from the previously published `tool_resolver.py`, `api/call.py`, `templates/tool_override.py`, and `agents_generator.py` variants. The affected callsite is the workflow include implementation in `praisonaiagents`, reached through the documented/covered `Include` workflow composition feature.&lt;/p&gt;
&lt;p&gt;## Affected Components&lt;/p&gt;
&lt;p&gt;- Package: `praisonaiagents`
- File: `praisonaiagents/workflows/workflows.py`
- Sink: `Workflow._execute_include()`
- Current affected callsite:&lt;/p&gt;
&lt;p&gt;```python
tools_py = recipe_path / &amp;#34;tools.py&amp;#34;
if tools_py.exists():
    spec = importlib.util.spec_from_file_location(&amp;#34;recipe_tools&amp;#34;, tools_py)
    recipe_module = importlib.util.module_from_spec(spec)
    spec.loader.exec_module(recipe_module)
```&lt;/p&gt;
&lt;p&gt;The current head also contains a similar unguarded workflow-local `tools.py…&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: praisonaiagents, PyPI: PraisonAI&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;PraisonAI&amp;#39;s workflow include implementation implicitly imports and executes an included recipe&amp;#39;s `tools.py` file even when the documented `tools.py` autoload opt-in is unset.&lt;/p&gt;
&lt;p&gt;This bypasses the hardening added for the prior automatic `tools.py` RCE advisory family. A workflow that includes an untrusted local recipe can execute arbitrary Python module-level code before any model call or child workflow execution.&lt;/p&gt;
&lt;p&gt;The same sink is reachable through the higher-level `praisonai.recipe.run()` recipe API when a steps-based recipe workflow includes a local child recipe. The supplementary PoV demonstrates this route without starting a network service or relying on external APIs.&lt;/p&gt;
&lt;p&gt;This is distinct from the previously published `tool_resolver.py`, `api/call.py`, `templates/tool_override.py`, and `agents_generator.py` variants. The affected callsite is the workflow include implementation in `praisonaiagents`, reached through the documented/covered `Include` workflow composition feature.&lt;/p&gt;
&lt;p&gt;## Affected Components&lt;/p&gt;
&lt;p&gt;- Package: `praisonaiagents`
- File: `praisonaiagents/workflows/workflows.py`
- Sink: `Workflow._execute_include()`
- Current affected callsite:&lt;/p&gt;
&lt;p&gt;```python
tools_py = recipe_path / &amp;#34;tools.py&amp;#34;
if tools_py.exists():
    spec = importlib.util.spec_from_file_location(&amp;#34;recipe_tools&amp;#34;, tools_py)
    recipe_module = importlib.util.module_from_spec(spec)
    spec.loader.exec_module(recipe_module)
```&lt;/p&gt;
&lt;p&gt;The current head also contains a similar unguarded workflow-local `tools.py…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://vulnerability.circl.lu/vuln/ghsa-hxmv-c4g6-5fqc</guid>
    </item>
  </channel>
</rss>
