The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns detected. The scripts package_skill.py and quick_validate.py perform routine file system operations and metadata validation using standard Python libraries (pathlib, zipfile, re).
[REMOTE_CODE_EXECUTION] (SAFE): No dynamic execution (eval/exec), subprocess calls, or remote downloads are present. All code is static and performs its stated purpose.
[DATA_EXFILTRATION] (SAFE): No network activity or access to sensitive system files was identified. File access is restricted to the skill directory provided by the user.
[PROMPT_INJECTION] (SAFE): The scripts do not process natural language instructions as part of an agent loop and contain no instructions targeting LLM behavior.

skill-creator