Which versions of Metagpt are affected by CVE-2026-4516?

Organizations using Foundation Agents MetaGPT should be aware of moderate risk from CVE-2026-4516, a injection vulnerability rated CVSS 6.3.

Is there a public PoC exploit available for CVE-2026-4516?

Yes, a public proof-of-concept exploit is available for CVE-2026-4516. Prioritise patching immediately. EPSS: 0.0%.

How to fix or mitigate CVE-2026-4516?

Within 30 days: Identify affected systems running Foundation Agents MetaGPT and apply vendor patches as part of regular patch cycle. Validate input sanitization for user-controlled parameters.

Metagpt CVE-2026-4516

Q: What is the CVSS score of CVE-2026-4516?

CVE-2026-4516 has a CVSS 4.0 base score of 2.1 (Low). CVSS vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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: 0.0%.

EUVD-2026-14252 LOW

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') (CWE-74)

2026-03-21 VulDB

GHSA-xwvj-r2ph-6xqj

Code Injection Metagpt

2.1

CVSS 4.0 · NVD

Severity by source

NVD PRIMARY

2.1 LOW

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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

Low

User Interaction

None

Scope

Lifecycle Timeline

Severity Changed

Apr 29, 2026 - 01:11 NVD

MEDIUM LOW

CVSS changed

Apr 29, 2026 - 01:11 NVD

6.3 (MEDIUM) 2.1 (LOW)

PoC Detected

Mar 23, 2026 - 14:31 vuln.today

Public exploit code

EUVD ID Assigned

Mar 21, 2026 - 15:15 euvd

EUVD-2026-14252

Analysis Generated

Mar 21, 2026 - 15:15 vuln.today

CVE Published

Mar 21, 2026 - 15:02 nvd

MEDIUM 6.3

DescriptionCVE.org

A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of the file metagpt/actions/di/write_analysis_code.py of the component DataInterpreter. The manipulation results in injection. It is possible to launch the attack remotely. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.

AnalysisAI

A code injection vulnerability exists in Foundation Agents MetaGPT up to version 0.8.1, specifically in the DataInterpreter component's write_analysis_code.py file, allowing authenticated attackers to inject and execute arbitrary code remotely. The vulnerability is classified as CWE-74 (Improper Neutralization of Special Elements in Output Used by a Downstream Component) with a CVSS score of 6.3 and requires low privileges and no user interaction. A public proof-of-concept exploit is available, indicating active research and potential real-world exploitation risk.

Technical ContextAI

The vulnerability resides in the MetaGPT framework (CPE: cpe:2.3:a:foundation_agents:metagpt:*:*:*:*:*:*:*:*), specifically within the DataInterpreter component's write_analysis_code.py module. The root cause is classified under CWE-74, which involves improper neutralization of special elements in output used by a downstream component—in this context, likely a failure to properly sanitize or validate code generation inputs before they are processed or executed by the interpreter. MetaGPT is an AI agent framework that generates code based on user prompts, making injection vectors particularly dangerous if user-supplied or external data is not properly escaped or validated before being incorporated into generated Python code that is subsequently executed.

RemediationAI

Immediately upgrade Foundation Agents MetaGPT to a version newer than 0.8.1 if available; however, given the lack of vendor response, verify patch availability on the official GitHub repository (https://github.com/geekan/MetaGPT) before upgrading. If no patched version is available, implement compensating controls by restricting network access to the MetaGPT service to only trusted internal users and networks, enforcing strong authentication mechanisms, and running MetaGPT in a sandboxed or containerized environment with minimal privilege escalation potential. Additionally, implement strict input validation and output encoding for any user-supplied data that may influence code generation within the DataInterpreter component, and monitor execution logs for suspicious code injection patterns. Consider forking the project or applying manual patches based on the public exploit analysis until an official fix is released.