Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple manual screen-time coaching aid with no evidence of hidden data collection, persistence, or unsafe system access.
Installers should understand this as a manual coaching template, not clinical care or device-management software. Users should provide only the screen-time details they are comfortable sharing; the inspected artifact does not collect telemetry or enforce app limits itself.
The description says to use the skill when someone 'feels trapped by scrolling, checking, or rebound screen behavior,' which is broad natural language that can overlap with many casual productivity or wellness requests. It does not provide explicit trigger phrases, scope limits, or negative examples clarifying when this skill should not activate.
The README presents the skill bilingually and includes a Chinese-only usage scenario alongside English scenarios, but it does not state whether the skill will adapt to the user's preferred language. This can create a natural-language policy concern if the skill implicitly forces or defaults to a language without explicit user opt-in.
The file introduces a Chinese alias and later includes a full Chinese usage scenario, but it does not state whether responses should follow the user's language preference or ask for consent before switching languages. This can violate language/locale policy expectations if the skill outputs a language the user did not request.
No suspicious patterns detected.
