Submit #773930: deepwisdom MetaGPT v0.8.1 Remote command executioninfo

Titledeepwisdom MetaGPT v0.8.1 Remote command execution
DescriptionA Remote Code Execution (RCE) vulnerability exists in the MetaGPT framework's DataInterpreter component due to insufficient input validation on user-provided prompts. An attacker can use prompt injection to manipulate the LLM into generating malicious Python code, which is then automatically executed in a Jupyter Notebook environment without any sandbox restrictions or security checks.
Source⚠️ https://github.com/Ka7arotto/cve/blob/main/MetaGPT-rce2.md
User
 Goku (UID 80486)
Submission03/06/2026 12:58 (5 months ago)
Moderation03/20/2026 15:40 (14 days later)
StatusAccepted
VulDB entry352081 [Foundation Agents MetaGPT up to 0.8.1 DataInterpreter write_analysis_code.py injection]
Points19

Want to know what is going to be exploited?

We predict KEV entries!