The Agent Skills Directory

[SAFE]: The skill performs legitimate cleanup operations to remove a previously installed service.
[COMMAND_EXECUTION]: The skill uses Bash to interact with system service managers (launchctl on macOS, systemctl --user on Linux) and delete files using rm. These actions are restricted to the current user's scope and do not involve privilege escalation (such as sudo).
[DATA_EXFILTRATION]: No network requests or access to sensitive credentials (e.g., SSH keys, AWS tokens) were detected.
[PROMPT_INJECTION]: The instructions are direct and do not contain patterns intended to bypass AI safety guardrails or override system prompts.

uninstall-watchdog