CVE-2024-23750
Code execution in metagpt
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
NVD Score used
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
- Record
CVE-2024-23750- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
CVE List
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
- Record
CVE-2024-23750- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
EUVDEUVD-2024-0100
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
- Record
EUVD-2024-0100- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-g7ph-8423-pf4j
Code execution in metagpt
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
- Record
GHSA-g7ph-8423-pf4j- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
OSV
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
- Record
CVE-2024-23750- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Updated
- 2026-11-02
OSVGHSA-g7ph-8423-pf4j
Code execution in metagpt
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
- Record
GHSA-g7ph-8423-pf4j- CVSS 3.1
- 8.8 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - Weakness
- CWE-94
- Updated
- 2026-11-02
OSVPYSEC-2024-9 No score
MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subprocess.Popen.
- Record
PYSEC-2024-9- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
metagptPyPI |
through 0.6.6 | None known |
metagptPyPI |
through 0.6.6, plus listed versions 0.10.3.00.4.00.5.00.5.1 Show 7 moreShow less0.5.20.6.00.6.10.6.20.6.30.6.40.6.5 |
None known |
metagptPyPI |
before 0.6.5, plus listed versions 0.10.3.00.4.00.5.00.5.1 Show 6 moreShow less0.5.20.6.00.6.10.6.20.6.30.6.4 |
0.6.5 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2024-23750 is a high vulnerability (CVSS 8.8) in Deepwisdom Metagpt, published January 22, 2024. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.96%, the 61st percentile. Fixed in metagpt 0.6.5.