Is there a patch available for EUVD-2026-21072?

Yes, a patch is available for EUVD-2026-21072. Update the affected software to the latest version immediately.

Metagpt EUVD-2026-21072

Q: What is the CVSS score of EUVD-2026-21072?

EUVD-2026-21072 has a CVSS 4.0 base score of 6.9 (Medium). CVSS vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. EPSS exploitation probability: 0.8%.

| CVE-2026-5974 MEDIUM

OS Command Injection (CWE-78)

2026-04-09 VulDB

GHSA-fcc8-4q7h-wvwc

Command Injection Metagpt

6.9

CVSS 4.0 · NVD

Severity by source

NVD PRIMARY

6.9 MEDIUM

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Lifecycle Timeline

EUVD ID Assigned

Apr 09, 2026 - 20:15 euvd

EUVD-2026-21072

Analysis Generated

Apr 09, 2026 - 20:15 vuln.today

Patch released

Apr 09, 2026 - 20:15 nvd

Patch available

CVE Published

Apr 09, 2026 - 19:30 nvd

MEDIUM 6.9

DescriptionCVE.org

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.1. The affected element is the function Bash.run in the library metagpt/tools/libs/terminal.py. This manipulation causes os command injection. The attack is possible to be carried out remotely. The project was informed of the problem early through a pull request but has not reacted yet.

AnalysisAI

Remote command injection in FoundationAgents MetaGPT versions up to 0.8.1 allows unauthenticated network attackers to execute arbitrary OS commands via the Bash.run function in metagpt/tools/libs/terminal.py. The vulnerability has a CVSS score of 6.9 with network-accessible attack vector and low complexity, and matches CISA SSVC criteria for partial technical impact with automatable exploitation; a proof-of-concept exists but no confirmed active exploitation has been reported.

Technical ContextAI

The vulnerability stems from improper input validation in the Bash.run function located in the MetaGPT library's terminal.py module. MetaGPT is an AI agent framework that processes user inputs to execute commands through a terminal interface. The root cause is classified as CWE-78 (Improper Neutralization of Special Elements used in an OS Command), which occurs when user-supplied data is passed unsanitized to OS command execution functions. The attack leverages the remote accessibility of the Bash.run interface, allowing an attacker to inject malicious shell metacharacters or command separators into parameters that are subsequently executed with the privileges of the MetaGPT process.

RemediationAI

Vendor-released patch status is listed as available; however, the specific patched version number is not independently confirmed from the provided data. Users should apply the fix referenced in GitHub PR #1940 (https://github.com/FoundationAgents/MetaGPT/pull/1940), which addresses the command injection in the Bash.run function. Organizations unable to patch immediately should implement network-level access controls to restrict who can send requests to MetaGPT services, sanitize all user inputs before passing them to the Bash.run function, and consider running MetaGPT in a sandboxed or containerized environment with minimal OS-level privileges. For the most current patch version and detailed mitigation guidance, consult the vendor's advisory and monitor the GitHub repository for official release updates.