The Agent Skills Directory

[SAFE]: No malicious patterns such as remote code execution, unauthorized network access, or data exfiltration were detected. The skill's components are designed for local development workflows and do not exhibit suspicious behavior.\n- [COMMAND_EXECUTION]: The skill includes Python scripts (init_skill.py, package_skill.py) that perform local file system operations including directory creation, file writing, and zipping. These actions are restricted to the local environment and are necessary for the skill's primary functionality.\n- [PROMPT_INJECTION]: The skill includes a surface for indirect prompt injection as it processes user-provided metadata and directory contents.\n
Ingestion points: Reads skill names and file paths from CLI arguments and reads SKILL.md content for validation in quick_validate.py.\n
Boundary markers: The SKILL.md template provided by init_skill.py uses clear [TODO: ...] placeholders to guide user input.\n
Capability inventory: The skill has capabilities to read and write files locally and create zip archives.\n
Sanitization: The skill implements best practices for processing untrusted data, specifically using yaml.safe_load() for frontmatter parsing and regex validation for skill identifiers in quick_validate.py.

skill-creator