Sandbox Bypass in PraisonAI Agents Enables Remote Code Execution

Publication date: 2026-04-03

Last updated on: 2026-04-14

Assigner: GitHub, Inc.

Description

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the _safe_getattr wrapper, achieving arbitrary OS command execution on the host. This issue has been patched in version 1.5.90.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-04-03

Last Modified

2026-04-14

Generated

2026-07-06

AI Q&A

2026-04-04

EPSS Evaluated

2026-07-05

NVD

CVE-2026-34938

Affected Vendors & Products

Vendor	Product	Version / Range
praison	praisonaiagents	to 1.5.90 (exc)

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-693	The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product.

Attack-Flow Graph

Impact Analysis

This vulnerability allows an attacker to achieve arbitrary OS command execution on the host running PraisonAI. This means an attacker can run any command on the affected system with potentially full control, leading to complete compromise of the host, data theft, data destruction, or further attacks within the network.

Executive Summary

PraisonAI is a multi-agent teams system. Before version 1.5.90, the execute_code() function in praisonai-agents runs attacker-controlled Python code inside a three-layer sandbox. However, this sandbox can be completely bypassed by using a string subclass with an overridden startswith() method passed to the _safe_getattr wrapper. This bypass allows an attacker to execute arbitrary operating system commands on the host machine.

Mitigation Strategies

The vulnerability has been patched in PraisonAI version 1.5.90. Immediate mitigation involves upgrading PraisonAI to version 1.5.90 or later.

Hi! I’m here to help you understand CVE-2026-34938. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70