The Agent Skills Directory

COMMAND_EXECUTION (SAFE): The scripts package_skill.py and quick_validate.py perform local file system operations such as reading files, creating directories, and generating zip archives. They do not execute arbitrary shell commands or call external processes.
DATA_EXFILTRATION (SAFE): There are no network operations, hardcoded credentials, or patterns suggesting the unauthorized transmission of data.
REMOTE_CODE_EXECUTION (SAFE): No remote code downloads or dynamic execution patterns were detected. The scripts use yaml.safe_load() for parsing configuration files, which is a secure practice that prevents code execution during deserialization.
PROMPT_INJECTION (SAFE): The documentation files (output-patterns.md, workflows.md) provide structural templates for skill output and logic but do not contain instructions that attempt to bypass AI safety guardrails.

skill-creator