The HAI Build Code Generator includes an automatic command execution feature with two options: 'Execute safe commands' and 'Execute all commands.' The 'safe commands' option relies on a model to classify commands as safe or potentially destructive. Due to prompt injection vulnerabilities, attackers can manipulate the input to cause the model to misclassify malicious commands as safe, thereby bypassing the user approval step and allowing arbitrary command execution. This vulnerability is identified as CWE-94 (Improper Control of Generation of Code). The CVSS 3.1 base score is 9.8, reflecting network attack vector, low attack complexity, no privileges or user interaction required, and high impact on confidentiality, integrity, and availability.

Successful exploitation allows remote attackers to execute arbitrary terminal commands on the affected system without user approval, potentially leading to full system compromise. The vulnerability affects confidentiality, integrity, and availability of the system. There are no known exploits in the wild at this time.

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, users should avoid enabling the 'Execute safe commands' automatic execution mode or restrict its use to trusted inputs only. Monitoring for suspicious command execution and applying strict input validation where possible may reduce risk.