79 matches found
GPT Researcher MCP STDIO configuration allows remote command execution
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...
PYSEC-2026-4219 GPT Researcher MCP STDIO configuration allows remote command execution
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...
CVE-2026-37006
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...
EUVD-2026-67270
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...
CVE-2026-37006
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...
CVE-2026-37006
A vulnerability exists in the WebSocket endpoint of gpt-researcher version v0.14.7 and before . This flaw allows an unauthenticated remote attacker to achieve code execution by leveraging malicious Model Context Protocol configurations . The provided documents do not specify a remediation, patch ...
CVE-2026-37006: Improper Authentication
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...
CVE-2026-37006
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...
PT-2026-82663
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...
CVE-2026-37006
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations...
GHSA-8J86-H8GG-797P GPT Researcher MCP STDIO configuration allows remote command execution
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...
EUVD-2025-210474
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...
GPT Researcher MCP STDIO configuration allows remote command execution
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...
PT-2026-105497
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...
CVE-2025-65720
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...
CVE-2025-65720
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...
CVE-2025-65720: Improper Neutralization of Special Elements used in a Command
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...
CVE-2025-65720
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...
PT-2026-60309
Name of the Vulnerable Software and Affected Versions GPT Researcher version 3.3.7 Description An issue allows attackers to execute arbitrary commands on a victim system through command injection. This occurs when a user interacts with a specially crafted HTML page, and no authentication is...