CVE-2026-0761 json
Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability
published 2026-01-23 9 mo ago modified 2026-06-17 4 mo 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.
CISA SSVC
- Exploitation
- none
- Automatable
- yes
- Technical impact
- total
- Assessed
- 9 mo ago
Exploit prediction
2.52% chance of exploitation in the next 30 days, higher than 84% of all scored CVEs (FIRST EPSS, 2026-11-08).
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
-
zerodayinitiative.com
/advisories/ZDI-26-027/
third-party-advisory
Sources
- CVE List CVE-2026-0761
- NVD CVE-2026-0761
Fencer Vulns 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.