praisonai
Affected
- introduced
0, fixed4.5.128(ecosystem)
Fixed versions
4.5.128
Fix
- Fixed version
4.5.128pip install --upgrade praisonai==4.5.128
Advisory
Also known as: CVE-2026-40156, GHSA-2g3w-cpc4-chr4
PraisonAI Vulnerable to Implicit Execution of Arbitrary Code via Automatic tools.py Loading
PraisonAI automatically loads a file named tools.py from the current working directory to discover and register custom agent tools. This loading process uses importlib.util.spec_from_file_location and immediately executes module-level code via spec.loader.exec_module() without explicit user consent, validation, or sandboxing.
The tools.py file is loaded implicitly, even when it is not referenced in configuration files or explicitly requested by the user. As a result, merely placing a file named tools.py in the working directory is sufficient to trigger code execution.
This behavior violates the expected security boundary between user-controlled project files (e.g., YAML configurations) and executable code, as untrusted content in the working directory is treated as trusted and executed automatically.
If an attacker can place a malicious tools.py file into a directory where a user or automated system (e.g., CI/CD pipeline) runs praisonai, arbitrary code execution occurs immediately upon startup, before any agent logic begins.
---
Vulnerable Code Location
src/praisonai/praisonai/tool_resolver.py → ToolResolver._load_local_tools
tools_path = Path(self._tools_py_path) # defaults to "tools.py" in CWD
...
spec = importlib.util.spec_from_file_location("tools", str(tools_path))
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module) # Executes arbitrary code
---
Reproducing the Attack
tools.py in the target directory:import os
# Executes immediately on import
print("[PWNED] Running arbitrary attacker code")
os.system("echo RCE confirmed > pwned.txt")
def dummy_tool():
return "ok"
agents.yaml.praisonai agents.yaml
[PWNED] is printedpwned.txt is created---
Real-world Impact
This issue introduces a software supply chain risk. If an attacker introduces a malicious tools.py into a repository (e.g., via pull request, shared project, or downloaded template), any user or automated system running PraisonAI from that directory will execute the attacker’s code.
Affected scenarios include:
Successful exploitation can lead to:
---
Remediation Steps
--load-tools) or config optiontools.pyHigh Basis: CVSS v3 score 7.8, vector CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
0, fixed 4.5.128 (ecosystem)4.5.128
4.5.128pip install --upgrade praisonai==4.5.128Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0