x-install

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs downloading and potentially executing remote install scripts and binaries from untrusted public sources (e.g., https://get.x-cmd.com and https://github.com/x-cmd/release) as part of its required workflow (see data/install.md and SKILL.md), and the agent is expected to review and act on that third-party content (including curl | sh auto-install), which could materially influence its actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime installation commands that fetch and execute remote code from https://get.x-cmd.com (e.g., "curl -fsSL https://get.x-cmd.com | sh") which the agent may run if instructed, creating a high-risk external dependency.