x-mirror

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

• Third-party content exposure detected (high risk: 0.90). The installation guide (data/install.md) explicitly directs fetching and executing remote scripts (e.g., "curl -fsSL https://get.x-cmd.com | sh") and downloading binaries from GitHub, so the agent may fetch and run untrusted third‑party content whose instructions can alter behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's installation instructions explicitly instruct fetching and executing remote code at runtime via "curl -fsSL https://get.x-cmd.com | sh" (and equivalent download+sh), which executes remote code from https://get.x-cmd.com and is a required dependency for the skill.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly directs configuring and switching mirrors for system package managers (apt, pacman, dnf, yum, apk, etc.), actions that typically modify system-level configuration files and require elevated privileges, so it can push the agent to change the machine state.