Vulnerability · Published Jan 23, 2026 · Assigned by zdi

CVE-2026-0761Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability

Critical 9.8

In plain English

A critical-severity code injection in MetaGPT from Foundation Agents. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 2.5% (higher than 85% of all known vulnerabilities).

Severity (CVSS 3.0)9.8Critical

Exploit odds (30 days)2.5%top 15.1% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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 (as reported)

Vendor	Product	Versions
Foundation Agents	MetaGPT	0.8.1

Weakness: CWE-94 · Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

ZDI-26-027 x_research-advisory