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

Critical 9.8 Published Updated

Remote attackers can execute arbitrary code via improper validation in the actionoutput_str_to_mapping function of MetaGPT.

Exploited in the wild
Not known
Login needed
Not needed
Attackable
Over the internet
Victim action needed
Not needed
Fix
None listed

What is CVE-2026-0761?

CVE-2026-0761 is a critical code injection vulnerability in Foundation Agents MetaGPT, published on 23 Jan 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

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.

Weakness: CWE-94

Which versions are affected by CVE-2026-0761?

It affects 1 product.

Products include Deepwisdom Metagpt.

How do I fix CVE-2026-0761?

No fix has been published for CVE-2026-0761 yet. Limit exposure of the affected software until one is available.

Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.

Is CVE-2026-0761 being exploited?

There is no known exploitation of CVE-2026-0761 in the wild and no public exploit code.

Sources

Also known as GHSA-rj73-q8hx-cvvm.

Is CVE-2026-0761 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free