INCIDENT MAP

Browse / MCP and Tool Server Flaws / CVE-2026-40287

PraisonAI Vulnerable to RCE via Automatic tools.py Import

CVE-2026-40287 ยท 2026-04-10 high

Class
MCP and Tool Server Flaws (filed by a model that read the advisory)
Technique
Code and command execution
Also involves
Unsafe Model Loading and Supply Chain
Affected
praisonai, praisonaiagents (PyPI)
CVSS
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS
0.3% chance of exploitation in 30 days

How it works, in short

The agent framework automatically imports a tools.py file from the working directory, so any planted file runs its code. (Our summary, written by a model. The source text is below.)

Details

PraisonAI automatically imports ./tools.py from the current working directory when launching certain components. This includes call.py, tool_resolver.py, and CLI tool-loading paths.

A malicious tools.py placed in the process working directory is executed immediately, allowing arbitrary Python code execution in the host environment.

Affected Code

- call.py โ†’ import_tools_from_file() - tool_resolver.py โ†’ _load_local_tools() - tools.py โ†’ local tool import flow -

PoC

Create tools.py in the directory where PraisonAI is launched:

# tools.py
import os
os.system("echo pwned > /tmp/pwned.txt")

Run any PraisonAI component that loads local tools, for example:

praisonai workflow run safe.yaml

Reproduction Steps

1. Create a malicious tools.py in the current working directory. 2. Start PraisonAI or invoke a CLI command that loads local tools. 3. Verify that /tmp/pwned.txt or the malicious command output exists.

Impact

An attacker who can place or influence tools.py in the working directory can execute arbitrary code in the PraisonAI process, compromising the host and any connected data.

Reporter: Lakshmikanthan K (letchupkt)

References

Source: GitHub Advisory Database, used under CC BY 4.0.