RCE in Deepwisdom Metagpt
CVE-2026-4515
A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function code_generate of the file metagpt/ext/aflow/scripts/operator.py. The manipulation leads to code injection. It is possible to initiate the at…
EPSS: 0.001 (17.7th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 6.3 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L.
Affected products
- Deepwisdom Metagpt
- Foundation Agents Metagpt — versions 0.8.0, 0.8.1
Weakness classification (CWE)
References
- VDB-352080 | Foundation Agents MetaGPT operator.py code_generate code injection (technical-description, Third Party Advisory, VDB Entry, vdb-entry)
- VDB-352080 | CTI Indicators (IOB, IOC, TTP, IOA) (signature, Permissions Required, permissions-required, VDB Entry)
- Submit #773929 | deepwisdom MetaGPT v0.8.1 Remote command execution (Third Party Advisory, VDB Entry, third-party-advisory)
- cna@vuldb.com (exploit, Broken Link)
Frequently asked questions
- What is CVE-2026-4515?
- CVE-2026-4515 is a medium-severity vulnerability in Deepwisdom Metagpt, classified under Improper Neutralization of Special Elements in Output Used by a Downstream Component (Injection). CVSS score: 6.3/10. Published 2026-03-21.
- How severe is CVE-2026-4515?
- Medium severity. CVSS v3 base score is 6.3 out of 10.