Executive Summary

PraisonAI before version 4.5.128 has a vulnerability that allows authenticated attackers to execute arbitrary shell commands on the system. This happens because the UI modules hardcode the approval_mode to auto, which overrides the administrator's configuration set via the PRAISON_APPROVAL_MODE environment variable. As a result, attackers can bypass the manual approval process and command sanitization blocklists by instructing the LLM agent to run shell commands using subprocess.run with shell=True.

Useful 0 Not Useful 0

Impact Analysis

This vulnerability can have severe impacts as it allows an authenticated attacker to execute arbitrary shell commands on the affected system without manual approval. This can lead to unauthorized access, data compromise, system manipulation, or further exploitation of the environment.

Useful 0 Not Useful 0