Command Injection Vulnerability in FoundationAgents MetaGPT Software
CVE-2026-11455

2.3LOW

Key Information:

Vendor

Foundationagents

Status
Metagpt
Vendor
CVE Published:
7 June 2026

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2026-11455?

A command injection vulnerability has been identified in FoundationAgents MetaGPT, specifically in the check_cmd_exists function located in the metagpt/utils/common.py file. This vulnerability arises from improper handling of the mermaid.path argument, potentially allowing remote attackers to execute arbitrary commands on the system. The complexity of exploiting this vulnerability is acknowledged as significant, making it particularly challenging for attackers. Despite being publicly disclosed, there has been no official response from the project team regarding the issue. For more information and mitigation strategies, please refer to the relevant security advisories.

Affected Version(s)

MetaGPT 0.8.0

MetaGPT 0.8.1

MetaGPT 0.8.2

Exploit Proof of Concept (PoC)

PoC code is written by security researchers to demonstrate the vulnerability can be exploited. PoC code is also a key component for weaponization which could lead to ransomware.

CVE-2026-11455 - Proof of Concept

References

https://vuldb.com/vuln/369074
vdb-entrytechnical-description
https://vuldb.com/vuln/369074/cti
signaturepermissions-required
https://vuldb.com/cve/CVE-2026-11455
third-party-advisory

CVSS V4

Score:
2.3
Severity:
LOW
Confidentiality:
Low
Integrity:
Low
Availability:
Low
Attack Vector:
Network
Attack Complexity:
High
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • 🟡

    Public PoC available

  • 👾

    Exploit known to exist

  • Vulnerability published

  • Vulnerability Reserved

Credit

ASUKA39 (VulDB User)
VulDB CNA Team
.