The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill provides legitimate utility scripts and documentation for agent skill development.\n- [COMMAND_EXECUTION]: The skill provides local Python utilities (scripts/init_skill.py, scripts/package_skill.py, scripts/quick_validate.py) intended for project scaffolding, validation, and packaging. These scripts perform standard file and directory operations within the user-specified project path.\n- [PROMPT_INJECTION]: The documentation includes guidance and templates for writing clear, AI-executable instructions. No instructions attempting to bypass safety filters or override system behavior were found.\n- [REMOTE_CODE_EXECUTION]: All code generation performed by the skill uses hardcoded local templates. There are no patterns involving remote script execution or downloads from untrusted sources.\n- [DATA_EXFILTRATION]: No network activity, credential harvesting, or unauthorized data access patterns were identified.

skill-creator