The Agent Skills Directory

[SAFE]: The skill is purely documentation-based and does not contain any executable code, scripts, or instructions to perform dangerous system operations. It includes explicit security guidelines (in references/operations/security.md) advising users to review remote scripts before execution and to avoid sharing credentials.
[EXTERNAL_DOWNLOADS]: The skill references official resources from the LinuxMirrors project (e.g., linuxmirrors.cn and github.com/SuperManito/LinuxMirrors). The evaluation-report.html file loads the Tailwind CSS library from a well-known service (cdn.tailwindcss.com). These references are for documentation and presentation purposes and do not trigger remote code execution.
[DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill instructions specifically state that it does not collect, store, or transmit user data and warns against requesting sensitive information like passwords or SSH keys.
[PROMPT_INJECTION]: No prompt injection or jailbreak attempts were found. The instructions are structured to provide authoritative information and maintain strict task boundaries.

linuxmirrors-awesome