CVE-2025-65720: GPT Researcher Remote Command Execution Vulnerability
Summary
CVE-2025-65720: GPT Researcher MCP STDIO configuration allows remote command execution. Affects gpt-researcher versions >= 0.14.5, <= 0.14.7. No fix is published. How to fix ↓
Check if this vulnerability affects your application
Upload a manifest or SBOM and we'll show whether you're affected, plus every other risky package in the same scan.
No signup required · Results in about 60 seconds
Background
GPT Researcher is an open-source tool designed for researchers to facilitate the exploration and analysis of data using advanced AI models. It allows users to interact with various datasets and perform complex queries. However, version 3.3.7 of GPT Researcher has a critical vulnerability that permits remote command execution, posing significant risks to user systems.
Vulnerability Detail
An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page. This vulnerability arises from improper handling of user input, which can be exploited by malicious actors to gain unauthorized access and control over the system. The potential ramifications include data breaches, system compromise, and unauthorized manipulation of system resources.
How To Fix
No fixed version is published for this vulnerability.
Tip — Not sure whether your app is affected? Vulert can check the versions your app actually runs. Scan free →
Workaround
As a temporary workaround, avoid interacting with untrusted HTML pages while using GPT Researcher. Additionally, consider implementing network security measures to restrict access to the application from untrusted sources.
Conclusion
The GPT Researcher vulnerability (CVE-2025-65720) presents a critical risk due to its potential for remote command execution. Users are strongly advised to update to the latest version to safeguard their systems. Utilizing tools like Vulert can help monitor and alert for such vulnerabilities in real-time.
See every vulnerability recorded for gpt-researcher →
FAQ
The CVSS score of this vulnerability is 9.8, indicating a critical level of severity.
You can use the Vulert playground at Vulert Scanner to check if your application is affected by this vulnerability without requiring any signup.
The potential impacts include unauthorized command execution, data breaches, and complete system compromise.
Yes, a patch is available. Update to version 0.14.8 or later of the GPT Researcher package to mitigate the vulnerability.
If immediate updates are not possible, avoid using the application with untrusted HTML content and implement network security measures to limit exposure.
