The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various system commands (docker, curl, ps, netstat, etc.) to perform its intended function of monitoring service and infrastructure health. These operations are limited to the local environment and are standard for diagnostic tools.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill uses the dynamic context injection syntax (!\docker compose ps...`) in the SKILL.md frontmatter to populate project context with service status. This is a legitimate use of the feature for development workflows and does not involve user-input injection or sensitive data exfiltration.\n- **[REMOTE_CODE_EXECUTION]:** A Python script scripts/health_check.py` is executed to generate health reports. Analysis of the script shows it performs local probes (HTTP status codes, disk usage via shutil, memory via /proc/meminfo or vm_stat) and uses subprocess to call trusted local binaries like docker and curl. It does not download or execute untrusted code from the internet.

health