Back

CRITICAL

Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability

Published Jan 23, 2026

Description

Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this vulnerability.

The specific flaw exists within the actionoutput_str_to_mapping function. The issue results from the lack of proper validation of a user-supplied string before using it to execute Python code. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-28124.

Affected products

Remediation

No remediation recorded yet.

Metrics

Weaknesses (1)

References (1)

Change history (0)

No recorded changes yet.

Sources
CVE.org / MITRE
Status PUBLISHED
Assigner zdi
Published Jan 23, 2026
Updated Jan 23, 2026
Reserved Jan 8, 2026
CISA Vulnrichment
Updated Jan 23, 2026
NVD
Status Analyzed
Modified Jun 17, 2026
Red Hat
Severity n/a
Public date n/a