CVE-2026-0761

CRITICAL LAB

Foundation Agents MetaGPT - Code Injection

Title source: llm

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.

Exploits (1)

github WORKING POC 1 stars
by exploitintel · pythonpoc
https://github.com/exploitintel/eip-pocs-and-cves/tree/main/CVE-2026-0761

Scores

CVSS v3 9.8
EPSS 0.0259
EPSS Percentile 85.3%
Attack Vector NETWORK
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Lab Environment

Lab screenshot
patched vulnerable
docker pull ghcr.io/exploitintel/cve-2026-0761-vulnerable:latest
All Labs GitHub

Classification

CWE
CWE-94
Status published

Affected Products (1)

deepwisdom/metagpt

Timeline

Published Jan 23, 2026
Tracked Since Feb 18, 2026