pythagora-io/gpt-pilot · Security
GPT-Pilot contains a command injection vulnerability in the Executor.run() method
- GHSA ID
- GHSA-m85w-whwh-qvfx
- CVE ID
- CVE-2026-31246
- Severity
- medium
- Published
- Updated
- CVSS
- 6.5 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
- CVSS v3
- 6.5 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
Description
GPT-Pilot thru commit 0819827ce20346ef5f25b3fe29293cb448840565 (2025-09-03) contains a command injection vulnerability (CWE-78) in the Executor.run() method. During project execution, when the system prompts the user to confirm or modify a command to be run, it accepts free-text input without proper validation. The user-supplied input is directly passed to asyncio.create_subprocess_shell() for execution. This allows an attacker to replace the intended command with arbitrary shell commands, leading to remote code execution with the privileges of the GPT-Pilot process.
CWEs
- CWE-78 · Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')