A path traversal vulnerability exists in the Ansible Lightspeed MCP server of Red Hat Ansible Automation Platform 2. The issue allows attackers to perform indirect prompt injection to manipulate an AI agent, resulting in unauthorized file writes outside intended directories. This can expose sensitive host information and enable limited command execution, potentially escalating to full system compromise. The CVSS 3.1 vector indicates local attack vector with low privileges required, user interaction needed, and high confidentiality impact with limited integrity and availability impacts. No official patch or remediation level is stated in the provided vendor advisory content.

Successful exploitation can lead to unauthorized file writes on the host system, exposing sensitive information and allowing execution of malicious commands. This may result in partial system compromise with potential for full system control. The confidentiality impact is high, integrity impact is low, and availability impact is low according to the CVSS vector.

Patch status is not yet confirmed — check the vendor advisory at https://access.redhat.com/security/cve/CVE-2026-44192 for current remediation guidance. No official fix or temporary mitigation is stated in the provided data. Until a patch is available, restrict access to the affected Ansible Automation Platform components and monitor for suspicious activity related to AI agent interactions.