OS Command Injection in FoundationAgents MetaGPT by FoundationAgents
CVE-2026-5973

6.9MEDIUM

Key Information:

Vendor

Foundationagents

Status
Metagpt
Vendor
CVE Published:
9 April 2026

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2026-5973?

A security vulnerability has been identified in FoundationAgents MetaGPT, specifically in the get_mime_type function located in the common.py file. This flaw allows for remote OS command injection, which can be exploited by attackers to execute arbitrary commands on the vulnerable system. Although the project team was made aware of this issue through a pull request, no remedial action has yet been taken to address the vulnerability. The exploit has been publicly disclosed, raising concerns over the safety of users still using affected versions.

Affected Version(s)

MetaGPT 0.8.0

MetaGPT 0.8.1

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-2026-5973 - Proof of Concept

References

https://vuldb.com/vuln/356527
vdb-entrytechnical-description
https://vuldb.com/vuln/356527/cti
signaturepermissions-required
https://vuldb.com/submit/791755
third-party-advisory

CVSS V4

Score:
6.9
Severity:
MEDIUM
Confidentiality:
Low
Integrity:
Low
Availability:
Low
Attack Vector:
Network
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • 🟡

    Public PoC available

  • 👾

    Exploit known to exist

  • Vulnerability published

  • Vulnerability Reserved

Credit

Eric-d (VulDB User)
VulDB CNA Team
.