The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard system monitoring commands such as uptime, ps, sysctl, and vm_stat. These operations are strictly read-only and consistent with the skill's stated purpose of system diagnosis.
[SAFE]: The skill incorporates explicit safety rules for interactive operations, such as requiring user confirmation before terminating processes and prohibiting the termination of critical system processes.
[DATA_EXFILTRATION]: No network-related commands (e.g., curl, wget) or patterns indicating data exfiltration to external domains were detected.
[PROMPT_INJECTION]: The instructions do not contain patterns attempting to bypass safety filters, override agent behavior, or extract system prompts.
[SAFE]: The logic for grouping processes using awk includes basic sanitization by extracting basenames and specific app patterns, which helps prevent display-based confusion.

system-doctor