CVE-2026-31246
Command Injection in GPT-Pilot
Publication date: 2026-05-11
Last updated on: 2026-05-11
Assigner: MITRE
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| pythagora-io | gpt-pilot | * |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-UNKNOWN |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
The vulnerability in GPT-Pilot is a command injection flaw found in the Executor.run() method. When the system asks the user to confirm or modify a command to be executed, it accepts free-text input without properly validating it. This user input is then directly passed to a shell execution function (asyncio.create_subprocess_shell()), allowing an attacker to inject and execute arbitrary shell commands.
This means an attacker can replace the intended command with malicious commands, leading to remote code execution with the same privileges as the GPT-Pilot process.
How can this vulnerability impact me? :
This vulnerability can have serious impacts because it allows an attacker to execute arbitrary commands on the system running GPT-Pilot. The attacker gains the same privileges as the GPT-Pilot process, which could lead to unauthorized access, data theft, system compromise, or further attacks within the network.
If exploited, it could result in loss of control over the affected system, potential data corruption, or disruption of services.