CVE-2026-5972Public exploitNetwork attack vector

Remote command execution via weak command blocklist

Published Apr 9, 2026 · Updated Apr 9, 2026

OS command injection in MetaGPT 0.8.0 through 0.8.1 allows remote attackers to execute shell commands through LLM-controlled input. Terminal.run_command filters only two fixed strings before writing the remaining command text directly to a persistent shell. Exploitation requires an agentic workflow in which external input can influence the LLM, after which commands run with the MetaGPT process privileges.

CVSS severity9.8
Critical
EPSS probability2.56%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

OS command injection in MetaGPT 0.8.0 through 0.8.1 allows remote attackers to execute shell commands through LLM-controlled input. Terminal.run_command filters only two fixed strings before writing the remaining command text directly to a persistent shell. Exploitation requires an agentic workflow in which external input can influence the LLM, after which commands run with the MetaGPT process privileges.

The record

CVE
CVE-2026-5972
Published
Apr 9, 2026
Updated
Apr 9, 2026
Vendor
Foundation Agents
Product
MetaGPT
Classifications
CWE-78, CWE-77, T1059
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Apr 9, 2026CVE publishedPublication date reported by the CVE source.
  2. Apr 9, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0.8.0
  2. Affected versionversion=0.8.1

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Foundation Agents · MetaGPTversion=0.8.0; version=0.8.1

Published CVSS scores

7.5VulDBAV:N/AC:L/Au:N/C:P/I:P/A:P
5.5VulDBCVSS: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:P
7.3VulDBCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
9.8NVDCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 9, 2026Sep 15, 2026
Latest reporting daySep 15, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-78Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
CWE-77Improper Neutralization of Special Elements used in a Command ('Command Injection')
T1059Command and Scripting Interpreter

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo