RCE in Deepwisdom Metagpt
CVE-2026-0761
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.
Vulnerability class: RCE (Remote Code Execution)
EPSS: 0.024 (83.3th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
Affected products
- Deepwisdom Metagpt — versions 0.8.1
- Foundation Agents Metagpt — versions 0.8.1
Weakness classification (CWE)
References
- zdi-disclosures@trendmicro.com (x_research-advisory, Third Party Advisory)
Frequently asked questions
- What is CVE-2026-0761?
- CVE-2026-0761 is a critical-severity vulnerability in Deepwisdom Metagpt, classified under Code Injection. CVSS score: 9.8/10. Published 2026-01-23.
- How severe is CVE-2026-0761?
- Critical severity. CVSS v3 base score is 9.8 out of 10.