Description
Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data 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 deserialize_message function. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-28121.
Published: 2026-01-23
Score: 9.8 Critical
EPSS: 2.2% Low
KEV: No
Impact: Remote Code Execution
Action: Immediate Patch
AI Analysis

Impact

The flaw lies in the deserialize_message function of Foundation Agents MetaGPT, which fails to validate user‑supplied data. An attacker can send a crafted serialized payload that, when processed, triggers arbitrary code execution. The vulnerability does not require authentication, allowing any network user who can reach the service to launch an exploit that runs with the service account's privileges.

Affected Systems

Foundation Agents MetaGPT version 0.8.1 is confirmed to contain the flaw, as indicated by the CPE. It is not known whether earlier releases are affected, but it is inferred that they might also be vulnerable because the deserialization routine was unchanged before 0.8.1.

Risk and Exploitability

The CVSS base score of 9.8 signals critical severity. The EPSS score of 2% indicates a moderate likelihood of exploitation, and the absence of authentication makes the attack vector remote over the network. The vulnerability is not yet listed in the CISA KEV catalog, so no specific exploitation code is known at this time.

Generated by OpenCVE AI on April 18, 2026 at 15:18 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Upgrade Foundation Agents MetaGPT to a patched version that addresses the deserialization flaw (for example, version 0.8.2 or later).
  • Limit network exposure of the MetaGPT service so that only trusted hosts can access the deserialize_message endpoint; enforce firewall rules or VPN isolation.
  • If an upgrade is not immediately possible, disable the deserialize_message function or replace it with a secure deserialization library that performs strict input validation.

Generated by OpenCVE AI on April 18, 2026 at 15:18 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Fri, 20 Feb 2026 13:45:00 +0000

Type Values Removed Values Added
First Time appeared Deepwisdom
Deepwisdom metagpt
CPEs cpe:2.3:a:deepwisdom:metagpt:0.8.1:*:*:*:*:*:*:*
Vendors & Products Deepwisdom
Deepwisdom metagpt

Fri, 23 Jan 2026 20:15:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Fri, 23 Jan 2026 16:45:00 +0000

Type Values Removed Values Added
First Time appeared Foundation Agents
Foundation Agents metagpt
Vendors & Products Foundation Agents
Foundation Agents metagpt

Fri, 23 Jan 2026 04:00:00 +0000

Type Values Removed Values Added
Description Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data 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 deserialize_message function. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-28121.
Title Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability
Weaknesses CWE-502
References
Metrics cvssV3_0

{'score': 9.8, 'vector': 'CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}

Subscriptions

Deepwisdom Metagpt
Foundation Agents Metagpt
cve-icon MITRE

Status: PUBLISHED

Assigner: zdi

Published:

Updated: 2026-01-23T19:25:33.145Z

Reserved: 2026-01-08T22:49:43.018Z

Link: CVE-2026-0760

cve-icon Vulnrichment

Updated: 2026-01-23T19:25:20.912Z

cve-icon NVD

Status : Analyzed

Published: 2026-01-23T04:16:02.707

Modified: 2026-02-20T13:42:12.430

Link: CVE-2026-0760

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-04-18T15:30:03Z

Weaknesses