https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Sat, 03 Oct 2026 12:57:23 +0000 https://cve.radiocsirt.org/vuln/cve-2026-40153 <p><strong>Affected:</strong> MervinPraison PraisonAIAgents</p> <p>PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the execute_command function in shell_tools.py calls os.path.expandvars() on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False (line 88) for security. This allows exfiltration of secrets stored in environment variables (database credentials, API keys, cloud access keys). The approval system displays the unexpanded $VAR references to human reviewers, creating a deceptive approval where the displayed command differs from what actually executes. This vulnerability is fixed in 1.5.128.</p> <p><strong>Affected:</strong> MervinPraison PraisonAIAgents</p> <p>PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the execute_command function in shell_tools.py calls os.path.expandvars() on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False (line 88) for security. This allows exfiltration of secrets stored in environment variables (database credentials, API keys, cloud access keys). The approval system displays the unexpanded $VAR references to human reviewers, creating a deceptive approval where the displayed command differs from what actually executes. This vulnerability is fixed in 1.5.128.</p> https://cve.radiocsirt.org/vuln/cve-2026-40153 https://cve.radiocsirt.org/vuln/ghsa-v8g7-9q6v-p3x8 <p><strong>Affected:</strong> PyPI: praisonaiagents</p> <p>## Summary</p> <p>The `execute_command` function in `shell_tools.py` calls `os.path.expandvars()` on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using `shell=False` (line 88) for security. This allows exfiltration of secrets stored in environment variables (database credentials, API keys, cloud access keys). The approval system displays the **unexpanded** `$VAR` references to human reviewers, creating a deceptive approval where the displayed command differs from what actually executes.</p> <p>## Details</p> <p>The vulnerable code is in `src/praisonai-agents/praisonaiagents/tools/shell_tools.py`:</p> <p>```python # Line 60: command is split command = shlex.split(command)</p> <p># Lines 62-64: VULNERABLE — expands ALL env vars in every argument # Expand tilde and environment variables in command arguments # (shell=False means the shell won&#39;t do this for us) command = [os.path.expanduser(os.path.expandvars(arg)) for arg in command]</p> <p># Line 88: shell=False is supposed to prevent shell feature access process = subprocess.Popen( command, ... shell=False, # Always use shell=False for security ) ```</p> <p>The security problem is a disconnect between the approval display and actual execution:</p> <p>1. The LLM generates a tool call: `execute_command(command=&#34;cat $DATABASE_URL&#34;)` 2. `_check_tool_approval_sync` in `tool_execution.py:558` passes `{&#34;command&#34;: &#34;cat $DATABASE_URL&#34;}` to the approval backend 3. `ConsoleBackend` (backends.py:81-85) displ…</p> <p><strong>Affected:</strong> PyPI: praisonaiagents</p> <p>## Summary</p> <p>The `execute_command` function in `shell_tools.py` calls `os.path.expandvars()` on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using `shell=False` (line 88) for security. This allows exfiltration of secrets stored in environment variables (database credentials, API keys, cloud access keys). The approval system displays the **unexpanded** `$VAR` references to human reviewers, creating a deceptive approval where the displayed command differs from what actually executes.</p> <p>## Details</p> <p>The vulnerable code is in `src/praisonai-agents/praisonaiagents/tools/shell_tools.py`:</p> <p>```python # Line 60: command is split command = shlex.split(command)</p> <p># Lines 62-64: VULNERABLE — expands ALL env vars in every argument # Expand tilde and environment variables in command arguments # (shell=False means the shell won&#39;t do this for us) command = [os.path.expanduser(os.path.expandvars(arg)) for arg in command]</p> <p># Line 88: shell=False is supposed to prevent shell feature access process = subprocess.Popen( command, ... shell=False, # Always use shell=False for security ) ```</p> <p>The security problem is a disconnect between the approval display and actual execution:</p> <p>1. The LLM generates a tool call: `execute_command(command=&#34;cat $DATABASE_URL&#34;)` 2. `_check_tool_approval_sync` in `tool_execution.py:558` passes `{&#34;command&#34;: &#34;cat $DATABASE_URL&#34;}` to the approval backend 3. `ConsoleBackend` (backends.py:81-85) displ…</p> https://cve.radiocsirt.org/vuln/ghsa-v8g7-9q6v-p3x8