The Agent Skills Directory

[SAFE]: The skill implements strong security measures for handling sensitive information. It correctly mandates the use of environment variables for API tokens rather than hardcoding them, writing them to files, or asking the user to provide them in chat.
[SAFE]: Command execution is handled securely. The provided Bash script uses shell arrays for curl arguments and employs --data-urlencode for all parameter passing. This effectively prevents shell injection and ensures that user-provided content (such as notification message bodies) is transmitted safely to the API without risk of character-set issues or command modification.
[SAFE]: The skill includes explicit instructions for human-in-the-loop confirmation for high-consequence actions, specifically for "Emergency Notifications" (priority 2), which bypass quiet hours and repeat until acknowledged.

pushover-notify