Monitor vulnerabilities like this one.
Sign up free to get alerted when software you use is affected.
6.9
MetaGPT up to 0.8.1 allows remote code execution
CVE-2026-6110
Summary
A security flaw in MetaGPT's thought generation feature could allow an attacker to execute arbitrary code on a server. This could happen if a malicious user sends a specially crafted request to the affected system. We recommend that users of MetaGPT version 0.8.1 or earlier update to the latest version as soon as possible to fix this issue.
Original title
A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. This affects the function generate_thoughts of the file metagpt/strategy/tot.py of the component Tree-of-Thought Solver. The ...
Original description
A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. This affects the function generate_thoughts of the file metagpt/strategy/tot.py of the component Tree-of-Thought Solver. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit is publicly available and might be used. The project was informed of the problem early through an issue report but has not responded yet.
nvd CVSS2.0
7.5
nvd CVSS3.1
7.3
nvd CVSS4.0
6.9
Vulnerability type
CWE-74
Injection
CWE-94
Code Injection
Published: 12 Apr 2026 · Updated: 12 Apr 2026 · First seen: 12 Apr 2026