RCE in Deepwisdom Metagpt

CVE-2026-5973

A vulnerability was found in FoundationAgents MetaGPT up to 0.8.1. Impacted is the function get_mime_type of the file metagpt/utils/common.py. The manipulation results in os command injection. The attack can be executed remotely. The exploit has been made public and could be used. The project was informed of the problem early through a pull request but has not reacted yet.

Vulnerability class: Command Injection (OS Command Injection)

EPSS: 0.025 (84.0th percentile) — read the EPSS interpretation.

CVSS v3 metric

CVSS v3 base score 7.3 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L.

Affected products

Weakness classification (CWE)

References

  • cna@vuldb.com (technical-description, VDB Entry, Third Party Advisory, vdb-entry)
  • cna@vuldb.com (signature, Permissions Required, permissions-required)
  • cna@vuldb.com (Exploit, VDB Entry, Third Party Advisory, third-party-advisory)
  • cna@vuldb.com (issue-tracking, Exploit, exploit, Mitigation, Issue Tracking)
  • cna@vuldb.com (issue-tracking, Patch, patch, Issue Tracking)
  • cna@vuldb.com (Product, product)

Frequently asked questions

What is CVE-2026-5973?
CVE-2026-5973 is a high-severity vulnerability in Deepwisdom Metagpt, classified under Command Injection. CVSS score: 7.3/10. Published 2026-04-09.
How severe is CVE-2026-5973?
High severity. CVSS v3 base score is 7.3 out of 10.