Skip to content
Fencer Intel
critical 9.8

CVE-2026-0761 json

Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability

published 9mo ago modified 4mo ago also EUVD-2026-4457

cvss
9.8
version 3.0, CNA
cisa kev
Not listed
not in CISA's catalog
epss
2.5%
EPSS 2.5% chance of exploitation in 30 days, percentile 84%
public exploits
0
none known

Summary

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.

Is CVE-2026-0761 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
total
Assessed
9mo ago

Exploit prediction

2.52% chance of exploitation in the next 30 days, higher than 84% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CNA 3.0 9.8 CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Affected products

  • Foundation Agents MetaGPT

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.