FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/tools/libs/terminal.py
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.
Affected software
Click a technology to see all vulnerabilities affecting it.
| Platform | Package | Vulnerable versions | Fixed in |
|---|---|---|---|
| Python (PyPI) | metagpt | <= 0.8.1 | no fix |
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-5974
- https://github.com/FoundationAgents/MetaGPT/issues/1931
- https://github.com/FoundationAgents/MetaGPT/pull/1940
- https://github.com/FoundationAgents/MetaGPT
- https://vuldb.com/submit/791758
- https://vuldb.com/vuln/356528
- https://vuldb.com/vuln/356528/cti
- https://pypi.org/project/metagpt
- https://github.com/advisories/GHSA-fcc8-4q7h-wvwc
- CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L- Weakness (CWE)
CWE-77- Platform
- Python (PyPI)
- Package
metagpt- Disclosed
- 09.04.2026
- Updated
- 11.10.2026 14:17
Sources and licenses
OSV / GitHub Advisory Database - PYSEC-2026-2639 - PyPA Advisory Database; CC BY 4.0
OSV / GitHub Advisory Database - GHSA-fcc8-4q7h-wvwc - CC BY 4.0
Vulnerability history: metagpt
All published vulnerabilities of this package (Python (PyPI)), newest first. Shows whether this is a one-off slip or a package that needs watching.
- Total entries
- 10
- First → latest
- 01.2024 06.2026
- Without a fix
- 8
- Exploited in attacks
- 0
Severity breakdown
- High 1
- Medium 6
- Low 3
Disclosures per year
- 2024: 1
- 2025: 0
- 2026: 9
-
FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/tools/libs/terminal.py this entry
Know which vulnerabilities affect your application
With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.