The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The script scripts/package_skill.py performs standard file system operations (reading files and creating zip archives) essential for its packaging functionality. It does not spawn shells or execute arbitrary user-provided commands.
[REMOTE_CODE_EXECUTION] (SAFE): Script scripts/quick_validate.py uses yaml.safe_load() to parse frontmatter, which is a secure practice that prevents arbitrary code execution during YAML deserialization.
[DATA_EXFILTRATION] (SAFE): No network operations or unauthorized file access patterns were detected. The script only accesses files within the designated skill folder.
[PROMPT_INJECTION] (SAFE): The markdown files in the references/ directory contain formatting templates and instructional examples. These are standard documentation patterns and do not attempt to override the agent's system instructions or safety filters.

skill-creator