Описание
A flaw was found in the Ansible Lightspeed Model Context Protocol (MCP) server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the user's system. This can result in the exposure of sensitive host information and enable the attacker to execute malicious commands, potentially leading to a full system compromise.
Отчет
Moderate: A path traversal vulnerability in the Visual Studio Code - Ansible Lightspeed Model Context Protocol (MCP) server allows an attacker to leverage indirect prompt injection to write files to arbitrary user-writable directories. This can lead to critical host data exfiltration or staged remote code execution when a user initiates an Ansible Execution Environment build, enabling access to sensitive host files or execution of malicious commands. Note the VS Code extension is distributed via VS Code Marketplace, not shipped in AAP RPMs or containers. The vulnerable code does not exist in any AAP-shipped artifact.
Меры по смягчению последствий
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Затронутые пакеты
| Платформа | Пакет | Состояние | Рекомендация | Релиз |
|---|---|---|---|---|
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-25/ansible-dev-tools-rhel8 | Not affected | ||
| Red Hat Ansible Automation Platform 2 | ansible-automation-platform-26/ansible-dev-tools-rhel9 | Not affected | ||
| Red Hat Ansible Automation Platform 2 | ansible-dev-tools | Not affected |
Показывать по
Дополнительная информация
Статус:
EPSS
6.6 Medium
CVSS3
Связанные уязвимости
A flaw was found in the Ansible Lightspeed Model Context Protocol (MCP) server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the user's system. This can result in the exposure of sensitive host information and enable the attacker to execute malicious commands, potentially leading to a full system compromise.
A flaw was found in the Ansible Lightspeed Model Context Protocol (MCP) server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the user's system. This can result in the exposure of sensitive host information and enable the attacker to execute malicious commands, potentially leading to a full system compromise.
EPSS
6.6 Medium
CVSS3