Advisory

PYSEC-2026-2895

Also known as: CVE-2026-40156, GHSA-2g3w-cpc4-chr4

Summary

PraisonAI Vulnerable to Implicit Execution of Arbitrary Code via Automatic tools.py Loading

Details

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

  1. Create a malicious 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"
  1. Create any valid agents.yaml.
  1. Run:
praisonai agents.yaml
  1. Observe:
  • [PWNED] is printed
  • pwned.txt is created
  • No warning or confirmation is shown

---

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:

  • CI/CD pipelines processing untrusted repositories
  • Shared development environments
  • AI workflow automation systems
  • Public project templates or examples

Successful exploitation can lead to:

  • Execution of arbitrary commands
  • Exfiltration of environment variables and credentials
  • Persistence mechanisms on developer or CI systems

---

Remediation Steps

  1. Require explicit opt-in for loading `tools.py`
  • Introduce a CLI flag (e.g., --load-tools) or config option
  • Disable automatic loading by default
  1. Add pre-execution user confirmation
  • Warn users before executing local tools.py
  • Allow users to decline execution
  1. Restrict trusted paths
  • Only load tools from explicitly defined project directories
  • Avoid defaulting to the current working directory
  1. Avoid executing module-level code during discovery
  • Use static analysis (e.g., AST parsing) to identify tool functions
  • Require explicit registration functions instead of import side effects
  1. Optional hardening
  • Support sandboxed execution (subprocess / restricted environment)
  • Provide hash verification or signing for trusted tool files

Severity

High 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

Dates

Published
2026-07-13 14:36 UTC
Modified
2026-07-13 16:32 UTC

Affected packages and fixes

praisonai

PyPI · All systems

Affected

  • introduced 0, fixed 4.5.128 (ecosystem)

Fixed versions

4.5.128

Fix

  • Fixed version 4.5.128
    pip install --upgrade praisonai==4.5.128

Fix 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

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences