Code Execution in Camel AI Toolkit via SubprocessInterpreter

Publication date: 2026-09-30

Last updated on: 2026-09-30

Assigner: MITRE

Description

In camel-ai camel 0.2.91a1, v0.2.91a2 and v0.2.91a3, CodeExecutionToolkit can run model-produced Python code through SubprocessInterpreter without an approval boundary.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-09-30

Last Modified

2026-09-30

Generated

2026-10-01

AI Q&A

2026-10-01

EPSS Evaluated

N/A

NVD

CVE-2026-51857

Affected Vendors & Products

Vendor	Product	Version / Range
camel-ai	camel	0.2.91a1
camel-ai	camel	0.2.91a2
camel-ai	camel	0.2.91a3

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-UNKNOWN

Attack-Flow Graph

Executive Summary

In camel-ai camel versions 0.2.91a1, v0.2.91a2, and v0.2.91a3, the CodeExecutionToolkit allows model-generated Python code to execute via SubprocessInterpreter without any approval checks. This means arbitrary code could run without user validation.

Impact Analysis

This vulnerability could allow attackers to execute malicious code on your system if you use the affected camel-ai versions. It bypasses security controls, potentially leading to data breaches or system compromise.

Mitigation Strategies

Immediately upgrade to a patched version of camel-ai camel if available. If not, disable CodeExecutionToolkit or SubprocessInterpreter functionality until a fix is released. Monitor official camel-ai channels for updates.

Hi! I’m here to help you understand CVE-2026-51857. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70