AI AgentHigh
CVE-2026-44192: A flaw was found in the Ansible Lightspeed Model Context Protocol (MCP) server. This vulnerability, …
- Occurred
- Jul 22, 2026
- Published
- Jul 22, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-44192
- cvss:MEDIUM
- agent-fail:injection-indirect
- agent-fail:authorization
- agent-cause:missing-guardrail
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: AI agent vulnerability allows indirect prompt injection leading to unauthorized file writes and system compromise.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8