CVE-2026-79408

Received Received - Intake

OS Command Injection in MetaGPT

Publication date: 2026-08-31

Last updated on: 2026-08-31

Assigner: MITRE

Description

An OS command injection vulnerability in MetaGPT 0.8.1 allows an attacker to execute arbitrary commands via the path argument of RepoParser.rebuild_class_views() in metagpt/repo_parser.py.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-08-31

Last Modified

2026-08-31

Generated

2026-09-01

AI Q&A

2026-09-01

EPSS Evaluated

N/A

NVD

CVE-2026-79408

Affected Vendors & Products

Vendor	Product	Version / Range
metagpt	metagpt	0.8.1

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-UNKNOWN

Attack-Flow Graph

Executive Summary

This is an OS command injection vulnerability in MetaGPT version 0.8.1. It allows an attacker to run arbitrary commands on the system by exploiting the path argument in the RepoParser.rebuild_class_views() function located in metagpt/repo_parser.py.

Impact Analysis

An attacker could execute malicious commands on your system, potentially leading to unauthorized access, data theft, or system compromise. This could affect the confidentiality, integrity, and availability of your data and services.

Compliance Impact

This vulnerability could lead to data breaches, which may violate GDPR and HIPAA requirements for data protection and security. Non-compliance could result in legal penalties, fines, and reputational damage.

Mitigation Strategies

Immediately update MetaGPT to a patched version if available. If no patch exists, disable or restrict access to the RepoParser.rebuild_class_views() function. Monitor network traffic for suspicious command execution attempts.

Hi! I’m here to help you understand CVE-2026-79408. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70