<?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://cve.radiocsirt.org</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>Tue, 06 Oct 2026 12:21:47 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-44339 — PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute</title>
      <link>https://cve.radiocsirt.org/vuln/cve-2026-44339</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; MervinPraison PraisonAI&lt;/p&gt;
&lt;p&gt;PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and __main__ after it fails to match the declared tool list and the registry. With the default agent configuration, _perm_allow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An attacker who can influence tool-call names can therefore invoke unintended application callables that were never declared as tools. This issue has been patched in praisonai version 4.6.37 and praisonaiagents version 1.6.37.&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 is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and __main__ after it fails to match the declared tool list and the registry. With the default agent configuration, _perm_allow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An attacker who can influence tool-call names can therefore invoke unintended application callables that were never declared as tools. This issue has been patched in praisonai version 4.6.37 and praisonaiagents version 1.6.37.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/cve-2026-44339</guid>
    </item>
    <item>
      <title>GHSA-gmjg-hv98-qggq — PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-gmjg-hv98-qggq</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: praisonaiagents, PyPI: PraisonAI&lt;/p&gt;
&lt;p&gt;### Summary
`praisonaiagents` resolves unresolved tool names against module globals and `__main__` after it fails to match the declared tool list and the registry. With the default agent configuration, `_perm_allow` is `None`, so undeclared non-dangerous tool names are not rejected by the permission gate. An attacker who can influence tool-call names can therefore invoke unintended application callables that were never declared as tools.&lt;/p&gt;
&lt;p&gt;### Details
The vulnerable resolution path is in [`[tool_execution.py](https://github.com/Users/shmulc/Documents/Codex/2026-05-03/please-go-over-tmp-tp-advisories/repos/PraisonAI/src/praisonai-agents/praisonaiagents/agent/tool_execution.py:734)`](/Users/shmulc/Documents/Codex/2026-05-03/please-go-over-tmp-tp-advisories/repos/PraisonAI/src/praisonai-agents/praisonaiagents/agent/tool_execution.py:734). After searching declared tools and the registry, execution falls back to `globals()` and then `__main__`:&lt;/p&gt;
&lt;p&gt;```python
func = None
for tool in self.tools if isinstance(self.tools, (list, tuple)) else []:
    ...&lt;/p&gt;
&lt;p&gt;if func is None:
    try:
        from ..tools.registry import get_registry
        registry = get_registry()
        func = registry.get(function_name)
    except ImportError:
        pass&lt;/p&gt;
&lt;p&gt;if func is None:
    func = globals().get(function_name)
    if not func:
        import __main__
        func = getattr(__main__, function_name, None)
```&lt;/p&gt;
&lt;p&gt;If a callable is found, it is executed directly:&lt;/p&gt;
&lt;p&gt;```python
elif callable(func):
    casted_a…&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
`praisonaiagents` resolves unresolved tool names against module globals and `__main__` after it fails to match the declared tool list and the registry. With the default agent configuration, `_perm_allow` is `None`, so undeclared non-dangerous tool names are not rejected by the permission gate. An attacker who can influence tool-call names can therefore invoke unintended application callables that were never declared as tools.&lt;/p&gt;
&lt;p&gt;### Details
The vulnerable resolution path is in [`[tool_execution.py](https://github.com/Users/shmulc/Documents/Codex/2026-05-03/please-go-over-tmp-tp-advisories/repos/PraisonAI/src/praisonai-agents/praisonaiagents/agent/tool_execution.py:734)`](/Users/shmulc/Documents/Codex/2026-05-03/please-go-over-tmp-tp-advisories/repos/PraisonAI/src/praisonai-agents/praisonaiagents/agent/tool_execution.py:734). After searching declared tools and the registry, execution falls back to `globals()` and then `__main__`:&lt;/p&gt;
&lt;p&gt;```python
func = None
for tool in self.tools if isinstance(self.tools, (list, tuple)) else []:
    ...&lt;/p&gt;
&lt;p&gt;if func is None:
    try:
        from ..tools.registry import get_registry
        registry = get_registry()
        func = registry.get(function_name)
    except ImportError:
        pass&lt;/p&gt;
&lt;p&gt;if func is None:
    func = globals().get(function_name)
    if not func:
        import __main__
        func = getattr(__main__, function_name, None)
```&lt;/p&gt;
&lt;p&gt;If a callable is found, it is executed directly:&lt;/p&gt;
&lt;p&gt;```python
elif callable(func):
    casted_a…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-gmjg-hv98-qggq</guid>
    </item>
  </channel>
</rss>
