GPT-Pilot versions up to commit 0819827ce20346ef5f25b3fe29293cb448840565 contain a command injection vulnerability (CWE-78) in the Executor.run() method. When the system prompts the user to confirm or modify a command, it accepts free-text input without validation. This input is passed directly to asyncio.create_subprocess_shell(), enabling an attacker to replace the intended command with arbitrary shell commands. This leads to remote code execution with the same privileges as the GPT-Pilot process.

Successful exploitation allows an attacker to execute arbitrary shell commands remotely with the privileges of the GPT-Pilot process. This can lead to full system compromise depending on the privileges of the process running GPT-Pilot. 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 a fix is available, avoid running untrusted input through the affected GPT-Pilot versions. Implement input validation or restrict usage to trusted users to reduce risk.